Data Browser¶
This page displays comprehensive information about all LLM providers and models, automatically generated from API data.
Statistics
Provider Count: 101 Model Count: 3182 Last Updated: 2/26/2026, 5:22:49 AM
Capabilities Legend: 🧠 Reasoning 🔧 Tools 📎 Attachment 🌡️ Temperature
302.AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| qwen3-235b-a22b-instruct-2507 | qwen3-235b-a22b-instruct-2507 | 128K | 65.5K | Input: $0.29 Output: $1.143 | Model: 0.145 Completion: 3.941 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-07-30 |
| gpt-5-pro | gpt-5-pro | 400K | 272K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-10-08 |
| claude-opus-4-5-20251101 | claude-opus-4-5-20251101 | 200K | 64K | Input: $5 Output: $25 | Model: 2.500 Completion: 5.000 | 📎 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-11-25 |
| Deepseek-Reasoner | deepseek-reasoner | 128K | 128K | Input: $0.29 Output: $0.43 | Model: 0.145 Completion: 1.483 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-01-20 |
| Qwen-Max-Latest | qwen-max-latest | 131.1K | 8.2K | Input: $0.343 Output: $1.372 | Model: 0.172 Completion: 4.000 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2024-04-03 Updated: 2025-01-25 |
| qwen3-max-2025-09-23 | qwen3-max-2025-09-23 | 258K | 65.5K | Input: $0.86 Output: $3.43 | Model: 0.430 Completion: 3.988 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-09-24 |
| grok-4-fast-reasoning | grok-4-fast-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 | Model: 0.100 Completion: 2.500 | 📎 🧠 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-09-23 |
| gemini-2.5-flash-lite-preview-09-2025 | gemini-2.5-flash-lite-preview-09-2025 | 1M | 65.5K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-09-26 |
| gpt-5.2-chat-latest | gpt-5.2-chat-latest | 128K | 16.4K | Input: $1.75 Output: $14 | Model: 0.875 Completion: 8.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-12-12 |
| claude-opus-4-1-20250805-thinking | claude-opus-4-1-20250805-thinking | 200K | 32K | Input: $15 Output: $75 | Model: 7.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-05-27 |
| qwen3-coder-480b-a35b-instruct | qwen3-coder-480b-a35b-instruct | 262.1K | 65.5K | Input: $0.86 Output: $3.43 | Model: 0.430 Completion: 3.988 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-07-23 |
| gemini-2.5-flash-preview-09-2025 | gemini-2.5-flash-preview-09-2025 | 1M | 65.5K | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 📎 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-09-26 |
| grok-4-1-fast-reasoning | grok-4-1-fast-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 | Model: 0.100 Completion: 2.500 | 📎 🧠 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-11-20 |
| GLM-4.5 | glm-4.5 | 128K | 98.3K | Input: $0.286 Output: $1.142 | Model: 0.143 Completion: 3.993 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-07-29 |
| gemini-2.5-flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 📎 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-06-17 |
| kimi-k2-0905-preview | kimi-k2-0905-preview | 262.1K | 262.1K | Input: $0.632 Output: $2.53 | Model: 0.316 Completion: 4.003 | 🔧 🌡️ | 2025-06 | In: text Out: text | Released: 2025-09-05 |
| grok-4-1-fast-non-reasoning | grok-4-1-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 | Model: 0.100 Completion: 2.500 | 📎 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-11-20 |
| gpt-5.1 | gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-11-14 |
| claude-sonnet-4-5-20250929-thinking | claude-sonnet-4-5-20250929-thinking | 200K | 64K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-09-30 |
| mistral-large-2512 | mistral-large-2512 | 128K | 262.1K | Input: $1.1 Output: $3.3 | Model: 0.550 Completion: 3.000 | 📎 🔧 🌡️ | 2024-12 | In: text, image Out: text | Released: 2025-12-16 |
| glm-4.6 | glm-4.6 | 200K | 131.1K | Input: $0.286 Output: $1.142 | Model: 0.143 Completion: 3.993 | 🔧 🌡️ | 2025-03 | In: text Out: text | Released: 2025-09-30 |
| gemini-3-flash-preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 | Model: 0.250 Completion: 6.000 | 📎 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-12-18 |
| gpt-4.1-nano | gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| doubao-seed-1-6-vision-250815 | doubao-seed-1-6-vision-250815 | 256K | 32K | Input: $0.114 Output: $1.143 | Model: 0.057 Completion: 10.026 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-09-30 |
| doubao-seed-1-6-thinking-250715 | doubao-seed-1-6-thinking-250715 | 256K | 16K | Input: $0.121 Output: $1.21 | Model: 0.060 Completion: 10.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-07-15 |
| doubao-seed-1-8-251215 | doubao-seed-1-8-251215 | 224K | 64K | Input: $0.114 Output: $0.286 | Model: 0.057 Completion: 2.509 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-12-18 |
| claude-sonnet-4-5-20250929 | claude-sonnet-4-5-20250929 | 200K | 64K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-09-29 |
| ministral-14b-2512 | ministral-14b-2512 | 128K | 128K | Input: $0.33 Output: $0.33 | Model: 0.165 Completion: 1.000 | 📎 🔧 🌡️ | 2024-12 | In: text, image Out: text | Released: 2025-12-16 |
| MiniMax-M2 | MiniMax-M2 | 1M | 128K | Input: $0.33 Output: $1.32 | Model: 0.165 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-26 |
| gpt-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 | Model: 0.875 Completion: 8.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-12-12 |
| gpt-4.1 | gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| gemini-2.5-flash-nothink | gemini-2.5-flash-nothink | 1M | 65.5K | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 📎 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-06-24 |
| Qwen3-235B-A22B | qwen3-235b-a22b | 128K | 16.4K | Input: $0.29 Output: $2.86 | Model: 0.145 Completion: 9.862 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04-29 |
| deepseek-v3.2 | deepseek-v3.2 | 128K | 8.2K | Input: $0.29 Output: $0.43 | Model: 0.145 Completion: 1.483 | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2025-12-01 |
| claude-opus-4-5-20251101-thinking | claude-opus-4-5-20251101-thinking | 200K | 64K | Input: $5 Output: $25 | Model: 2.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-11-25 |
| claude-haiku-4-5-20251001 | claude-haiku-4-5-20251001 | 200K | 64K | Input: $1 Output: $5 | Model: 0.500 Completion: 5.000 | 📎 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-10-16 |
| gpt-5 | gpt-5 | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-08-08 |
| Deepseek-Chat | deepseek-chat | 128K | 8.2K | Input: $0.29 Output: $0.43 | Model: 0.145 Completion: 1.483 | 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-11-29 |
| gpt-4.1-mini | gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 | Model: 0.200 Completion: 4.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| gemini-2.5-flash-image | gemini-2.5-flash-image | 32.8K | 32.8K | Input: $0.3 Output: $30 | Model: 0.150 Completion: 100.000 | 📎 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-10-08 |
| gemini-3-pro-image-preview | gemini-3-pro-image-preview | 32.8K | 64K | Input: $2 Output: $120 | Model: 1.000 Completion: 60.000 | 📎 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-11-20 |
| glm-4.7 | glm-4.7 | 200K | 131.1K | Input: $0.286 Output: $1.142 | Model: 0.143 Completion: 3.993 | 🔧 🌡️ | 2025-06 | In: text Out: text | Released: 2025-12-22 |
| MiniMax-M1 | MiniMax-M1 | 1M | 128K | Input: $0.132 Output: $1.254 | Model: 0.066 Completion: 9.500 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-06-16 |
| kimi-k2-thinking | kimi-k2-thinking | 262.1K | 262.1K | Input: $0.575 Output: $2.3 | Model: 0.287 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Released: 2025-09-05 |
| gpt-5-thinking | gpt-5-thinking | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-08-08 |
| DeepSeek-V3.2-Thinking | deepseek-v3.2-thinking | 128K | 128K | Input: $0.29 Output: $0.43 | Model: 0.145 Completion: 1.483 | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2025-12-01 |
| chatgpt-4o-latest | chatgpt-4o-latest | 128K | 16.4K | Input: $5 Output: $15 | Model: 2.500 Completion: 3.000 | 📎 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-08-08 |
| Qwen-Plus | qwen-plus | 1M | 32.8K | Input: $0.12 Output: $1.2 | Model: 0.060 Completion: 10.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-07-23 |
| MiniMax-M2.1 | MiniMax-M2.1 | 1M | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-19 |
| kimi-k2-thinking-turbo | kimi-k2-thinking-turbo | 262.1K | 262.1K | Input: $1.265 Output: $9.119 | Model: 0.632 Completion: 7.209 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Released: 2025-09-05 |
| gemini-3-pro-preview | gemini-3-pro-preview | 1M | 64K | Input: $2 Output: $12 | Model: 1.000 Completion: 6.000 | 📎 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-11-19 |
| gemini-2.0-flash-lite | gemini-2.0-flash-lite | 2M | 8.2K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 📎 🌡️ | 2024-11 | In: text, image Out: text | Released: 2025-06-16 |
| doubao-seed-code-preview-251028 | doubao-seed-code-preview-251028 | 256K | 32K | Input: $0.17 Output: $1.14 | Model: 0.085 Completion: 6.706 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-11-11 |
| Qwen3-30B-A3B | qwen3-30b-a3b | 128K | 8.2K | Input: $0.11 Output: $1.08 | Model: 0.055 Completion: 9.818 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04-29 |
| grok-4-fast-non-reasoning | grok-4-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 | Model: 0.100 Completion: 2.500 | 📎 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-09-23 |
| gpt-5-mini | gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 | Model: 0.125 Completion: 8.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-08-08 |
| GLM-4.5V | glm-4.5v | 64K | 16.4K | Input: $0.29 Output: $0.86 | Model: 0.145 Completion: 2.966 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-07-29 |
| Qwen-Flash | qwen-flash | 1M | 32.8K | Input: $0.022 Output: $0.22 | Model: 0.011 Completion: 10.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-28 |
| GLM-4.6V | glm-4.6v | 128K | 32.8K | Input: $0.145 Output: $0.43 | Model: 0.072 Completion: 2.966 | 📎 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-12-08 |
| gpt-5.1-chat-latest | gpt-5.1-chat-latest | 128K | 16.4K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-11-14 |
| claude-opus-4-1-20250805 | claude-opus-4-1-20250805 | 200K | 32K | Input: $15 Output: $75 | Model: 7.500 Completion: 5.000 | 📎 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-08-05 |
| gemini-2.5-pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-06-17 |
| gpt-4o | gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 |
| grok-4.1 | grok-4.1 | 200K | 64K | Input: $2 Output: $10 | Model: 1.000 Completion: 5.000 | 📎 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-11-18 |
Abacus¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 2.0 Pro Exp | gemini-2.0-pro-exp-02-05 | 2M | 8.2K | - | - | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-02-05 |
| GPT-4o (2024-11-20) | gpt-4o-2024-11-20 | 128K | 16.4K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image, audio Out: text | Released: 2024-11-20 |
| Claude Opus 4.5 | claude-opus-4-5-20251101 | 200K | 64K | Input: $5 Output: $25 | Model: 2.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-01 |
| GPT-4o Mini | gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-07-18 |
| GPT-5.2 Chat Latest | gpt-5.2-chat-latest | 400K | 128K | Input: $1.5 Output: $12 | Model: 0.750 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2026-01-01 |
| Grok 4 | grok-4-0709 | 256K | 16.4K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-07-09 |
| Grok Code Fast 1 | grok-code-fast-1 | 256K | 16.4K | Input: $0.2 Output: $1.5 | Model: 0.100 Completion: 7.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-09-01 |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| Grok 4.1 Fast (Non-Reasoning) | grok-4-1-fast-non-reasoning | 2M | 16.4K | Input: $0.2 Output: $0.5 | Model: 0.100 Completion: 2.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-11-17 |
| GPT-5.1 | gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Gemini 2.0 Flash | gemini-2.0-flash-001 | 1M | 8.2K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-02-05 |
| o3 | o3 | 200K | 100K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 | Model: 0.250 Completion: 6.000 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-12-17 |
| Claude Opus 4 | claude-opus-4-20250514 | 200K | 32K | Input: $15 Output: $75 | Model: 7.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, pdf Out: text | Released: 2025-05-14 |
| GPT-4.1 Nano | gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| Claude Sonnet 4.5 | claude-sonnet-4-5-20250929 | 200K | 64K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 | Model: 0.875 Completion: 8.000 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-4.1 | gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| o3-pro | o3-pro | 200K | 100K | Input: $20 Output: $80 | Model: 10.000 Completion: 4.000 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-06-10 |
| Claude Sonnet 3.7 | claude-3-7-sonnet-20250219 | 200K | 64K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2024-10-31 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 200K | 64K | Input: $1 Output: $5 | Model: 0.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| GPT-5 | gpt-5 | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| o4-mini | o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 | Model: 0.550 Completion: 4.000 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-4.1 Mini | gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 | Model: 0.200 Completion: 4.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| Llama 3.3 70B Versatile | llama-3.3-70b-versatile | 128K | 32.8K | Input: $0.59 Output: $0.79 | Model: 0.295 Completion: 1.339 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-06 |
| Kimi K2 Turbo Preview | kimi-k2-turbo-preview | 256K | 8.2K | Input: $0.15 Output: $8 | Model: 0.075 Completion: 53.333 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-08 |
| Qwen 2.5 Coder 32B | qwen-2.5-coder-32b | 128K | 8.2K | Input: $0.79 Output: $0.79 | Model: 0.395 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-11 |
| Route LLM | route-llm | 128K | 16.4K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-01-01 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 65K | Input: $2 Output: $12 | Model: 1.000 Completion: 6.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-06-01 |
| o3-mini | o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 | Model: 0.550 Completion: 4.000 | 🧠 🔧 | 2024-05 | In: text Out: text | Released: 2024-12-20 Updated: 2025-01-29 |
| Qwen3 Max | qwen3-max | 131.1K | 16.4K | Input: $1.2 Output: $6 | Model: 0.600 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-05-28 |
| Grok 4 Fast (Non-Reasoning) | grok-4-fast-non-reasoning | 2M | 16.4K | Input: $0.2 Output: $0.5 | Model: 0.100 Completion: 2.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-07-09 |
| GPT-5 Mini | gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 | Model: 0.125 Completion: 8.000 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| Claude Sonnet 4 | claude-sonnet-4-20250514 | 200K | 64K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, pdf Out: text | Released: 2025-05-14 |
| GPT-5.1 Chat Latest | gpt-5.1-chat-latest | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Claude Opus 4.1 | claude-opus-4-1-20250805 | 200K | 32K | Input: $15 Output: $75 | Model: 7.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Gemini 2.5 Pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-25 |
| GPT-5 Nano | gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 | Model: 0.025 Completion: 8.000 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GLM-4.5 | zai-org/glm-4.5 | 128K | 8.2K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.6 | zai-org/glm-4.6 | 128K | 8.2K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-01 |
| GLM-4.7 | zai-org/glm-4.7 | 128K | 8.2K | Input: $0.7 Output: $2.5 | Model: 0.350 Completion: 3.571 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-01 |
| DeepSeek R1 | deepseek-ai/DeepSeek-R1 | 128K | 8.2K | Input: $3 Output: $7 | Model: 1.500 Completion: 2.333 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-20 |
| DeepSeek V3.2 | deepseek-ai/DeepSeek-V3.2 | 128K | 8.2K | Input: $0.27 Output: $0.4 | Model: 0.135 Completion: 1.481 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-15 |
| DeepSeek V3.1 Terminus | deepseek-ai/DeepSeek-V3.1-Terminus | 128K | 8.2K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-01 |
| DeepSeek V3.1 | deepseek/deepseek-v3.1 | 128K | 8.2K | Input: $0.14 Output: $0.28 | Model: 0.070 Completion: 2.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-20 |
| Llama 3.1 8B Instruct | meta-llama/Meta-Llama-3.1-8B-Instruct | 128K | 4.1K | Input: $0.02 Output: $0.05 | Model: 0.010 Completion: 2.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama 3.1 405B Instruct Turbo | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | 128K | 4.1K | Input: $3.5 Output: $3.5 | Model: 1.750 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama 4 Maverick 17B 128E Instruct FP8 | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 1M | 32.8K | Input: $0.14 Output: $0.59 | Model: 0.070 Completion: 4.214 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Llama 3.1 70B Instruct | meta-llama/Meta-Llama-3.1-70B-Instruct | 128K | 4.1K | Input: $0.4 Output: $0.4 | Model: 0.200 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-23 |
| QwQ 32B | Qwen/QwQ-32B | 32.8K | 32.8K | Input: $0.4 Output: $0.4 | Model: 0.200 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-28 |
| Qwen3 Coder 480B A35B Instruct | Qwen/qwen3-coder-480b-a35b-instruct | 262.1K | 65.5K | Input: $0.29 Output: $1.2 | Model: 0.145 Completion: 4.138 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-22 |
| Qwen3 32B | Qwen/Qwen3-32B | 128K | 8.2K | Input: $0.09 Output: $0.29 | Model: 0.045 Completion: 3.222 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-29 |
| Qwen 2.5 72B Instruct | Qwen/Qwen2.5-72B-Instruct | 128K | 8.2K | Input: $0.11 Output: $0.38 | Model: 0.055 Completion: 3.455 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09-19 |
| Qwen3 235B A22B Instruct | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262.1K | 8.2K | Input: $0.13 Output: $0.6 | Model: 0.065 Completion: 4.615 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-01 |
| GPT-OSS 120B | openai/gpt-oss-120b | 128K | 32.8K | Input: $0.08 Output: $0.44 | Model: 0.040 Completion: 5.500 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-08-05 |
AIHubMix¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 235B A22B Instruct 2507 | qwen3-235b-a22b-instruct-2507 | 262.1K | 262.1K | Input: $0.28 Output: $1.12 | Model: 0.140 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-30 |
| GPT-5-Codex | gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| GPT-5-Pro | gpt-5-pro | 400K | 128K | Input: $7 Output: $28 Cache Read: $3.5 | Model: 3.500 Completion: 4.000 Cache: 0.500 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| GPT-5.1-Codex-Max | gpt-5.1-codex-max | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Claude Opus 4.1 | claude-opus-4-1 | 200K | 32K | Input: $16.5 Output: $82.5 Cache Read: $1.5 Cache Write: $18.75 | Model: 8.250 Completion: 5.000 Cache: 0.091 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Qwen3 Coder 480B A35B Instruct | qwen3-coder-480b-a35b-instruct | 262.1K | 131K | Input: $0.82 Output: $3.29 | Model: 0.410 Completion: 4.012 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-01 |
| GPT-5.2-Codex | gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08-31 | In: text, image Out: text | Released: 2026-01-14 |
| Claude Opus 4.6 | claude-opus-4-6 | 200K | 128K | Input: $5 Output: $25 Cache Read: $0.3 Cache Write: $3.75 | Model: 2.500 Completion: 5.000 Cache: 0.060 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Coding GLM 4.7 Free | coding-glm-4.7-free | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| Coding MiniMax M2.1 Free | coding-minimax-m2.1-free | 204.8K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | 65K | Input: $0.075 Output: $0.3 Cache Read: $0.02 | Model: 0.037 Completion: 4.000 Cache: 0.267 | 📎 🔧 🌡️ | 2025-04 | In: text, image, audio, video Out: text | Released: 2025-09-15 |
| Claude Opus 4.6 Think | claude-opus-4-6-think | 200K | 128K | Input: $5 Output: $25 Cache Read: $0.3 Cache Write: $3.75 | Model: 2.500 Completion: 5.000 Cache: 0.060 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| GPT-5.1 | gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-11 | In: text, image Out: text | Released: 2025-11-15 |
| MiniMax M2.1 | minimax-m2.1 | 204.8K | 131.1K | Input: $0.29 Output: $1.15 | Model: 0.145 Completion: 3.966 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| GPT-4.1 nano | gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 Cache Read: $0.03 | Model: 0.050 Completion: 4.000 Cache: 0.300 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| Gemini 3 Pro Preview Search | gemini-3-pro-preview-search | 1M | 65K | Input: $2 Output: $12 Cache Read: $0.5 | Model: 1.000 Completion: 6.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-11 | In: text, image, audio, video Out: text | Released: 2025-11-19 |
| GPT-5.1 Codex Mini | gpt-5.1-codex-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 🌡️ | 2025-11 | In: text, image Out: text | Released: 2025-11-15 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| DeepSeek-V3.2-Think | deepseek-v3.2-think | 131K | 64K | Input: $0.3 Output: $0.45 | Model: 0.150 Completion: 1.500 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| Kimi K2.5 | kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 Cache Read: $0.1 | Model: 0.300 Completion: 5.000 Cache: 0.167 | 📎 🧠 🔧 🌡️ | 2025-07 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 0905 | Kimi-K2-0905 | 262.1K | 262.1K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| GPT-4.1 | gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| DeepSeek-V3.2 | deepseek-v3.2 | 131K | 64K | Input: $0.3 Output: $0.45 | Model: 0.150 Completion: 1.500 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| Qwen3 Max | qwen3-max-2026-01-23 | 262.1K | 65.5K | Input: $0.34 Output: $1.37 | Model: 0.170 Completion: 4.029 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-09-23 |
| GPT-5 | gpt-5 | 400K | 128K | Input: $5 Output: $20 Cache Read: $2.5 | Model: 2.500 Completion: 4.000 Cache: 0.500 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| o4-mini | o4-mini | 200K | 65.5K | Input: $1.5 Output: $6 Cache Read: $0.75 | Model: 0.750 Completion: 4.000 Cache: 0.500 | 🧠 | 2024-09 | In: text Out: text | Released: 2025-09-15 |
| GPT-4.1 mini | gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GLM-4.7 | glm-4.7 | 204.8K | 131.1K | Input: $0.27 Output: $1.1 Cache Read: $0.548 | Model: 0.135 Completion: 4.074 Cache: 2.030 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200K | 64K | Input: $1.1 Output: $5.5 Cache Read: $0.11 Cache Write: $1.25 | Model: 0.550 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| GPT-5.1 Codex | gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 🌡️ | 2025-11 | In: text, image Out: text | Released: 2025-11-15 |
| Claude Opus 4.5 | claude-opus-4-5 | 200K | 32K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-11-25 |
| Qwen3 235B A22B Thinking 2507 | qwen3-235b-a22b-thinking-2507 | 262.1K | 262.1K | Input: $0.28 Output: $2.8 | Model: 0.140 Completion: 10.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-30 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 65K | Input: $2 Output: $12 Cache Read: $0.5 | Model: 1.000 Completion: 6.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-11 | In: text, image, audio, video Out: text | Released: 2025-11-19 |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 200K | 64K | Input: $3.3 Output: $16.5 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.650 Completion: 5.000 Cache: 0.091 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| GPT-5-Mini | gpt-5-mini | 200K | 64K | Input: $1.5 Output: $6 Cache Read: $0.75 | Model: 0.750 Completion: 4.000 Cache: 0.500 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| DeepSeek-V3.2-Fast | deepseek-v3.2-fast | 128K | 128K | Input: $1.1 Output: $3.29 | Model: 0.550 Completion: 2.991 | - | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| GLM-4.6V | glm-4.6v | 128K | 32.8K | Input: $0.14 Output: $0.41 | Model: 0.070 Completion: 2.929 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-12-08 |
| Coding-GLM-4.7 | coding-glm-4.7 | 204.8K | 131.1K | Input: $0.27 Output: $1.1 Cache Read: $0.548 | Model: 0.135 Completion: 4.074 Cache: 2.030 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| Gemini 2.5 Pro | gemini-2.5-pro | 2M | 65K | Input: $1.25 Output: $5 Cache Read: $0.31 | Model: 0.625 Completion: 4.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, audio, video Out: text | Released: 2025-09-15 |
| GPT-5-Nano | gpt-5-nano | 128K | 16.4K | Input: $0.5 Output: $2 Cache Read: $0.25 | Model: 0.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| Claude Sonnet 4.6 Think | claude-sonnet-4-6-think | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| GPT-4o | gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 Updated: 2024-08-06 |
Alibaba¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Qwen-VL Plus | qwen-vl-plus | 131.1K | 8.2K | Input: $0.21 Output: $0.63 | Model: 0.105 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-01-25 Updated: 2025-08-15 |
| Qwen-VL Max | qwen-vl-max | 131.1K | 8.2K | Input: $0.8 Output: $3.2 | Model: 0.400 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-04-08 Updated: 2025-08-13 |
| Qwen3-Next 80B-A3B (Thinking) | qwen3-next-80b-a3b-thinking | 131.1K | 32.8K | Input: $0.5 Output: $6 | Model: 0.250 Completion: 12.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09 |
| Qwen3-Coder 480B-A35B Instruct | qwen3-coder-480b-a35b-instruct | 262.1K | 65.5K | Input: $1.5 Output: $7.5 | Model: 0.750 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen3 14B | qwen3-14b | 131.1K | 8.2K | Input: $0.35 Output: $1.4 Reasoning: $4.2 | Model: 0.175 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen3 Coder Flash | qwen3-coder-flash | 1M | 65.5K | Input: $0.3 Output: $1.5 | Model: 0.150 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-07-28 |
| Qwen3-VL 30B-A3B | qwen3-vl-30b-a3b | 131.1K | 32.8K | Input: $0.2 Output: $0.8 Reasoning: $2.4 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image Out: text | Open Weights Released: 2025-04 |
| Qwen3-ASR Flash | qwen3-asr-flash | 53.2K | 4.1K | Input: $0.035 Output: $0.035 | Model: 0.018 Completion: 1.000 | - | 2024-04 | In: audio Out: text | Released: 2025-09-08 |
| Qwen Max | qwen-max | 32.8K | 8.2K | Input: $1.6 Output: $6.4 | Model: 0.800 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-04-03 Updated: 2025-01-25 |
| Qwen Turbo | qwen-turbo | 1M | 16.4K | Input: $0.05 Output: $0.2 Reasoning: $0.5 | Model: 0.025 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-11-01 Updated: 2025-04-28 |
| Qwen2.5 7B Instruct | qwen2-5-7b-instruct | 131.1K | 8.2K | Input: $0.175 Output: $0.7 | Model: 0.087 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen2.5-VL 72B Instruct | qwen2-5-vl-72b-instruct | 131.1K | 8.2K | Input: $2.8 Output: $8.4 | Model: 1.400 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Open Weights Released: 2024-09 |
| Qwen2.5 14B Instruct | qwen2-5-14b-instruct | 131.1K | 8.2K | Input: $0.35 Output: $1.4 | Model: 0.175 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen3 8B | qwen3-8b | 131.1K | 8.2K | Input: $0.18 Output: $0.7 Reasoning: $2.1 | Model: 0.090 Completion: 3.889 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen3 32B | qwen3-32b | 131.1K | 16.4K | Input: $0.7 Output: $2.8 Reasoning: $8.4 | Model: 0.350 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen3.5 397B-A17B | qwen3.5-397b-a17b | 262.1K | 65.5K | Input: $0.6 Output: $3.6 Reasoning: $3.6 | Model: 0.300 Completion: 6.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2026-02-16 |
| QVQ Max | qvq-max | 131.1K | 8.2K | Input: $1.2 Output: $4.8 | Model: 0.600 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-03-25 |
| Qwen2.5-Omni 7B | qwen2-5-omni-7b | 32.8K | 2K | Input: $0.1 Output: $0.4 Input Audio: $6.76 | Model: 3.380 Completion: 0.059 | 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Open Weights Released: 2024-12 |
| Qwen2.5-VL 7B Instruct | qwen2-5-vl-7b-instruct | 131.1K | 8.2K | Input: $0.35 Output: $1.05 | Model: 0.175 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Open Weights Released: 2024-09 |
| Qwen-Omni Turbo Realtime | qwen-omni-turbo-realtime | 32.8K | 2K | Input: $0.27 Output: $1.07 Input Audio: $4.44 Output Audio: $8.89 | Model: 2.220 Completion: 2.002 | 🔧 🌡️ | 2024-04 | In: text, image, audio Out: text, audio | Released: 2025-05-08 |
| Qwen3 235B-A22B | qwen3-235b-a22b | 131.1K | 16.4K | Input: $0.7 Output: $2.8 Reasoning: $8.4 | Model: 0.350 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen3-Coder 30B-A3B Instruct | qwen3-coder-30b-a3b-instruct | 262.1K | 65.5K | Input: $0.45 Output: $2.25 | Model: 0.225 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen-Omni Turbo | qwen-omni-turbo | 32.8K | 2K | Input: $0.07 Output: $0.27 Input Audio: $4.44 Output Audio: $8.89 | Model: 2.220 Completion: 2.002 | 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Released: 2025-01-19 Updated: 2025-03-26 |
| Qwen-MT Plus | qwen-mt-plus | 16.4K | 8.2K | Input: $2.46 Output: $7.37 | Model: 1.230 Completion: 2.996 | 🌡️ | 2024-04 | In: text Out: text | Released: 2025-01 |
| Qwen3-VL Plus | qwen3-vl-plus | 262.1K | 32.8K | Input: $0.2 Output: $1.6 Reasoning: $4.8 | Model: 0.100 Completion: 8.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image Out: text | Released: 2025-09-23 |
| Qwen3-LiveTranslate Flash Realtime | qwen3-livetranslate-flash-realtime | 53.2K | 4.1K | Input: $10 Output: $10 Input Audio: $10 Output Audio: $38 | Model: 5.000 Completion: 3.800 | 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Released: 2025-09-22 |
| Qwen Plus | qwen-plus | 1M | 32.8K | Input: $0.4 Output: $1.2 Reasoning: $4 | Model: 0.200 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-01-25 Updated: 2025-09-11 |
| Qwen2.5 32B Instruct | qwen2-5-32b-instruct | 131.1K | 8.2K | Input: $0.7 Output: $2.8 | Model: 0.350 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen3-Next 80B-A3B Instruct | qwen3-next-80b-a3b-instruct | 131.1K | 32.8K | Input: $0.5 Output: $2 | Model: 0.250 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09 |
| Qwen3.5 Plus | qwen3.5-plus | 1M | 65.5K | Input: $0.4 Output: $2.4 Reasoning: $2.4 | Model: 0.200 Completion: 6.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Released: 2026-02-16 |
| Qwen3 Max | qwen3-max | 262.1K | 65.5K | Input: $1.2 Output: $6 | Model: 0.600 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-09-23 |
| Qwen3-Omni Flash | qwen3-omni-flash | 65.5K | 16.4K | Input: $0.43 Output: $1.66 Input Audio: $3.81 Output Audio: $15.11 | Model: 1.905 Completion: 3.966 | 🧠 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Released: 2025-09-15 |
| Qwen3 Coder Plus | qwen3-coder-plus | 1M | 65.5K | Input: $1 Output: $5 | Model: 0.500 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen Flash | qwen-flash | 1M | 32.8K | Input: $0.05 Output: $0.4 | Model: 0.025 Completion: 8.000 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2025-07-28 |
| Qwen2.5 72B Instruct | qwen2-5-72b-instruct | 131.1K | 8.2K | Input: $1.4 Output: $5.6 | Model: 0.700 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen3-Omni Flash Realtime | qwen3-omni-flash-realtime | 65.5K | 16.4K | Input: $0.52 Output: $1.99 Input Audio: $4.57 Output Audio: $18.13 | Model: 2.285 Completion: 3.967 | 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Released: 2025-09-15 |
| Qwen-VL OCR | qwen-vl-ocr | 34.1K | 4.1K | Input: $0.72 Output: $0.72 | Model: 0.360 Completion: 1.000 | 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-10-28 Updated: 2025-04-13 |
| QwQ Plus | qwq-plus | 131.1K | 8.2K | Input: $0.8 Output: $2.4 | Model: 0.400 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2025-03-05 |
| Qwen3-VL 235B-A22B | qwen3-vl-235b-a22b | 131.1K | 32.8K | Input: $0.7 Output: $2.8 Reasoning: $8.4 | Model: 0.350 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image Out: text | Open Weights Released: 2025-04 |
| Qwen Plus Character (Japanese) | qwen-plus-character-ja | 8.2K | 512 | Input: $0.5 Output: $1.4 | Model: 0.250 Completion: 2.800 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-01 |
| Qwen-MT Turbo | qwen-mt-turbo | 16.4K | 8.2K | Input: $0.16 Output: $0.49 | Model: 0.080 Completion: 3.063 | 🌡️ | 2024-04 | In: text Out: text | Released: 2025-01 |
| DeepSeek R1 | deepseek-r1 | 128K | - | Input: $4 Output: $16 | Model: 2.000 Completion: 4.000 | - | - | In: text Out: text | - |
Alibaba (China)¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Qwen-VL Plus | qwen-vl-plus | 131.1K | 8.2K | Input: $0.115 Output: $0.287 | Model: 0.058 Completion: 2.496 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-01-25 Updated: 2025-08-15 |
| Qwen-VL Max | qwen-vl-max | 131.1K | 8.2K | Input: $0.23 Output: $0.574 | Model: 0.115 Completion: 2.496 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-04-08 Updated: 2025-08-13 |
| Qwen Math Plus | qwen-math-plus | 4.1K | 3.1K | Input: $0.574 Output: $1.721 | Model: 0.287 Completion: 2.998 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-08-16 Updated: 2024-09-19 |
| DeepSeek V3.1 | deepseek-v3-1 | 131.1K | 65.5K | Input: $0.574 Output: $1.721 | Model: 0.287 Completion: 2.998 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| Qwen2.5-Coder 7B Instruct | qwen2-5-coder-7b-instruct | 131.1K | 8.2K | Input: $0.144 Output: $0.287 | Model: 0.072 Completion: 1.993 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-11 |
| Qwen3-Next 80B-A3B (Thinking) | qwen3-next-80b-a3b-thinking | 131.1K | 32.8K | Input: $0.144 Output: $1.434 | Model: 0.072 Completion: 9.958 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09 |
| DeepSeek V3 | deepseek-v3 | 65.5K | 8.2K | Input: $0.287 Output: $1.147 | Model: 0.143 Completion: 3.997 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| Qwen3-Coder 480B-A35B Instruct | qwen3-coder-480b-a35b-instruct | 262.1K | 65.5K | Input: $0.861 Output: $3.441 | Model: 0.430 Completion: 3.997 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen Long | qwen-long | 10M | 8.2K | Input: $0.072 Output: $0.287 | Model: 0.036 Completion: 3.986 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2025-01-25 |
| Qwen3 14B | qwen3-14b | 131.1K | 8.2K | Input: $0.144 Output: $0.574 Reasoning: $1.434 | Model: 0.072 Completion: 3.986 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| QwQ 32B | qwq-32b | 131.1K | 8.2K | Input: $0.287 Output: $0.861 | Model: 0.143 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-12 |
| Qwen3 Coder Flash | qwen3-coder-flash | 1M | 65.5K | Input: $0.144 Output: $0.574 | Model: 0.072 Completion: 3.986 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-07-28 |
| Qwen3-VL 30B-A3B | qwen3-vl-30b-a3b | 131.1K | 32.8K | Input: $0.108 Output: $0.431 Reasoning: $1.076 | Model: 0.054 Completion: 3.991 | 🧠 🔧 🌡️ | 2025-04 | In: text, image Out: text | Open Weights Released: 2025-04 |
| Qwen3-ASR Flash | qwen3-asr-flash | 53.2K | 4.1K | Input: $0.032 Output: $0.032 | Model: 0.016 Completion: 1.000 | - | 2024-04 | In: audio Out: text | Released: 2025-09-08 |
| Qwen Max | qwen-max | 131.1K | 8.2K | Input: $0.345 Output: $1.377 | Model: 0.172 Completion: 3.991 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-04-03 Updated: 2025-01-25 |
| DeepSeek R1 Distill Qwen 14B | deepseek-r1-distill-qwen-14b | 32.8K | 16.4K | Input: $0.144 Output: $0.431 | Model: 0.072 Completion: 2.993 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| Moonshot Kimi K2 Instruct | moonshot-kimi-k2-instruct | 131.1K | 8.2K | Input: $0.574 Output: $2.294 | Model: 0.287 Completion: 3.997 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-01 |
| Qwen Doc Turbo | qwen-doc-turbo | 131.1K | 8.2K | Input: $0.087 Output: $0.144 | Model: 0.043 Completion: 1.655 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-01 |
| Qwen Turbo | qwen-turbo | 1M | 16.4K | Input: $0.044 Output: $0.087 Reasoning: $0.431 | Model: 0.022 Completion: 1.977 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-11-01 Updated: 2025-07-15 |
| Qwen2.5 7B Instruct | qwen2-5-7b-instruct | 131.1K | 8.2K | Input: $0.072 Output: $0.144 | Model: 0.036 Completion: 2.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen2.5-VL 72B Instruct | qwen2-5-vl-72b-instruct | 131.1K | 8.2K | Input: $2.294 Output: $6.881 | Model: 1.147 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Open Weights Released: 2024-09 |
| Tongyi Intent Detect V3 | tongyi-intent-detect-v3 | 8.2K | 1K | Input: $0.058 Output: $0.144 | Model: 0.029 Completion: 2.483 | 🌡️ | 2024-04 | In: text Out: text | Released: 2024-01 |
| Qwen2.5 14B Instruct | qwen2-5-14b-instruct | 131.1K | 8.2K | Input: $0.144 Output: $0.431 | Model: 0.072 Completion: 2.993 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| DeepSeek R1 0528 | deepseek-r1-0528 | 131.1K | 16.4K | Input: $0.574 Output: $2.294 | Model: 0.287 Completion: 3.997 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-05-28 |
| Qwen3 8B | qwen3-8b | 131.1K | 8.2K | Input: $0.072 Output: $0.287 Reasoning: $0.717 | Model: 0.036 Completion: 3.986 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| DeepSeek R1 | deepseek-r1 | 131.1K | 16.4K | Input: $0.574 Output: $2.294 | Model: 0.287 Completion: 3.997 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| Qwen3 32B | qwen3-32b | 131.1K | 16.4K | Input: $0.287 Output: $1.147 Reasoning: $2.868 | Model: 0.143 Completion: 3.997 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen3.5 397B-A17B | qwen3.5-397b-a17b | 262.1K | 65.5K | Input: $0.43 Output: $2.58 Reasoning: $2.58 | Model: 0.215 Completion: 6.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2026-02-16 |
| QVQ Max | qvq-max | 131.1K | 8.2K | Input: $1.147 Output: $4.588 | Model: 0.574 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-03-25 |
| Qwen2.5-Omni 7B | qwen2-5-omni-7b | 32.8K | 2K | Input: $0.087 Output: $0.345 Input Audio: $5.448 | Model: 2.724 Completion: 0.063 | 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Open Weights Released: 2024-12 |
| Qwen Plus Character | qwen-plus-character | 32.8K | 4.1K | Input: $0.115 Output: $0.287 | Model: 0.058 Completion: 2.496 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-01 |
| DeepSeek R1 Distill Llama 70B | deepseek-r1-distill-llama-70b | 32.8K | 16.4K | Input: $0.287 Output: $0.861 | Model: 0.143 Completion: 3.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| Qwen2.5-VL 7B Instruct | qwen2-5-vl-7b-instruct | 131.1K | 8.2K | Input: $0.287 Output: $0.717 | Model: 0.143 Completion: 2.498 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Open Weights Released: 2024-09 |
| Moonshot Kimi K2.5 | kimi-k2.5 | 262.1K | 32.8K | Input: $0.574 Output: $2.411 | Model: 0.287 Completion: 4.200 | 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-01-27 |
| Qwen-Omni Turbo Realtime | qwen-omni-turbo-realtime | 32.8K | 2K | Input: $0.23 Output: $0.918 Input Audio: $3.584 Output Audio: $7.168 | Model: 1.792 Completion: 2.000 | 🔧 🌡️ | 2024-04 | In: text, image, audio Out: text, audio | Released: 2025-05-08 |
| DeepSeek V3.2 Exp | deepseek-v3-2-exp | 131.1K | 65.5K | Input: $0.287 Output: $0.431 | Model: 0.143 Completion: 1.502 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| DeepSeek R1 Distill Llama 8B | deepseek-r1-distill-llama-8b | 32.8K | 16.4K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| Qwen3 235B-A22B | qwen3-235b-a22b | 131.1K | 16.4K | Input: $0.287 Output: $1.147 Reasoning: $2.868 | Model: 0.143 Completion: 3.997 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen3-Coder 30B-A3B Instruct | qwen3-coder-30b-a3b-instruct | 262.1K | 65.5K | Input: $0.216 Output: $0.861 | Model: 0.108 Completion: 3.986 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen-Omni Turbo | qwen-omni-turbo | 32.8K | 2K | Input: $0.058 Output: $0.23 Input Audio: $3.584 Output Audio: $7.168 | Model: 1.792 Completion: 2.000 | 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Released: 2025-01-19 Updated: 2025-03-26 |
| Qwen-MT Plus | qwen-mt-plus | 16.4K | 8.2K | Input: $0.259 Output: $0.775 | Model: 0.130 Completion: 2.992 | 🌡️ | 2024-04 | In: text Out: text | Released: 2025-01 |
| Qwen2.5-Math 7B Instruct | qwen2-5-math-7b-instruct | 4.1K | 3.1K | Input: $0.144 Output: $0.287 | Model: 0.072 Completion: 1.993 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| DeepSeek R1 Distill Qwen 1.5B | deepseek-r1-distill-qwen-1-5b | 32.8K | 16.4K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| DeepSeek R1 Distill Qwen 7B | deepseek-r1-distill-qwen-7b | 32.8K | 16.4K | Input: $0.072 Output: $0.144 | Model: 0.036 Completion: 2.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| Moonshot Kimi K2 Thinking | kimi-k2-thinking | 262.1K | 16.4K | Input: $0.574 Output: $2.294 | Model: 0.287 Completion: 3.997 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-11-06 |
| DeepSeek R1 Distill Qwen 32B | deepseek-r1-distill-qwen-32b | 32.8K | 16.4K | Input: $0.287 Output: $0.861 | Model: 0.143 Completion: 3.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 |
| Qwen Deep Research | qwen-deep-research | 1M | 32.8K | Input: $7.742 Output: $23.367 | Model: 3.871 Completion: 3.018 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-01 |
| Qwen3-VL Plus | qwen3-vl-plus | 262.1K | 32.8K | Input: $0.143353 Output: $1.433525 Reasoning: $4.300576 | Model: 0.072 Completion: 10.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image Out: text | Released: 2025-09-23 |
| Qwen2.5-Math 72B Instruct | qwen2-5-math-72b-instruct | 4.1K | 3.1K | Input: $0.574 Output: $1.721 | Model: 0.287 Completion: 2.998 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen Plus | qwen-plus | 1M | 32.8K | Input: $0.115 Output: $0.287 Reasoning: $1.147 | Model: 0.058 Completion: 2.496 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-01-25 Updated: 2025-09-11 |
| Qwen2.5 32B Instruct | qwen2-5-32b-instruct | 131.1K | 8.2K | Input: $0.287 Output: $0.861 | Model: 0.143 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen3-Next 80B-A3B Instruct | qwen3-next-80b-a3b-instruct | 131.1K | 32.8K | Input: $0.144 Output: $0.574 | Model: 0.072 Completion: 3.986 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09 |
| Qwen3.5 Plus | qwen3.5-plus | 1M | 65.5K | Input: $0.573 Output: $3.44 Reasoning: $3.44 | Model: 0.286 Completion: 6.003 | 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Released: 2026-02-16 |
| Qwen3 Max | qwen3-max | 262.1K | 65.5K | Input: $0.861 Output: $3.441 | Model: 0.430 Completion: 3.997 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-09-23 |
| Qwen3-Omni Flash | qwen3-omni-flash | 65.5K | 16.4K | Input: $0.058 Output: $0.23 Input Audio: $3.584 Output Audio: $7.168 | Model: 1.792 Completion: 2.000 | 🧠 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text, audio | Released: 2025-09-15 |
| Qwen Math Turbo | qwen-math-turbo | 4.1K | 3.1K | Input: $0.287 Output: $0.861 | Model: 0.143 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-09-19 |
| Qwen Flash | qwen-flash | 1M | 32.8K | Input: $0.022 Output: $0.216 | Model: 0.011 Completion: 9.818 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2025-07-28 |
| Qwen2.5 72B Instruct | qwen2-5-72b-instruct | 131.1K | 8.2K | Input: $0.574 Output: $1.721 | Model: 0.287 Completion: 2.998 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-09 |
| Qwen3-Omni Flash Realtime | qwen3-omni-flash-realtime | 65.5K | 16.4K | Input: $0.23 Output: $0.918 Input Audio: $3.584 Output Audio: $7.168 | Model: 1.792 Completion: 2.000 | 🔧 🌡️ | 2024-04 | In: text, image, audio Out: text, audio | Released: 2025-09-15 |
| Qwen-VL OCR | qwen-vl-ocr | 34.1K | 4.1K | Input: $0.717 Output: $0.717 | Model: 0.358 Completion: 1.000 | 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-10-28 Updated: 2025-04-13 |
| QwQ Plus | qwq-plus | 131.1K | 8.2K | Input: $0.23 Output: $0.574 | Model: 0.115 Completion: 2.496 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2025-03-05 |
| Qwen3-VL 235B-A22B | qwen3-vl-235b-a22b | 131.1K | 32.8K | Input: $0.286705 Output: $1.14682 Reasoning: $2.867051 | Model: 0.143 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image Out: text | Open Weights Released: 2025-04 |
| Qwen-MT Turbo | qwen-mt-turbo | 16.4K | 8.2K | Input: $0.101 Output: $0.28 | Model: 0.051 Completion: 2.772 | 🌡️ | 2024-04 | In: text Out: text | Released: 2025-01 |
| Qwen2.5-Coder 32B Instruct | qwen2-5-coder-32b-instruct | 131.1K | 8.2K | Input: $0.287 Output: $0.861 | Model: 0.143 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-11 |
| Qwen3 Coder Plus | qwen3-coder-plus | 1M | 65.5K | Input: $1 Output: $5 | Model: 0.500 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
aliyun-bailian¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| animate-anyone-gen2 | animate-anyone-gen2 | - | - | Per Second Standard: ¥0.08 | Model: 0.080 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| animate-anyone-template-gen2 | animate-anyone-template-gen2 | - | - | Per Second Standard: ¥0.08 | Model: 0.080 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| cosyvoice-v1 | cosyvoice-v1 | - | - | ¥2/10K chars | Model: 2.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| cosyvoice-v2 | cosyvoice-v2 | - | - | ¥2/10K chars | Model: 2.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| cosyvoice-v3-plus | cosyvoice-v3-plus | - | - | ¥2/10K chars | Model: 2.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| cosyvoice-v3 | cosyvoice-v3 | - | - | ¥0.4/10K chars | Model: 0.400 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| fun-asr-2025-08-25 | fun-asr-2025-08-25 | - | - | ¥0.00022/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| fun-asr-mtl-2025-08-25 | fun-asr-mtl-2025-08-25 | - | - | ¥0.00022/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| fun-asr-mtl | fun-asr-mtl | - | - | ¥0.00022/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| fun-asr-realtime-2025-09-15 | fun-asr-realtime-2025-09-15 | - | - | ¥0.00033/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| fun-asr-realtime | fun-asr-realtime | - | - | ¥0.00033/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| fun-asr | fun-asr | - | - | ¥0.00022/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| gte-rerank-v2 | gte-rerank-v2 | - | - | Input: ¥0.8 Output: - | Model: 0.400 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| image-out-painting | image-out-painting | - | - | ¥0.18/img | Model: 0.180 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| multimodal-embedding-v1 | multimodal-embedding-v1 | - | - | Text: ¥0.7/1K Image: ¥0.9/1K | - | - | - | In: text Out: text | - |
| paraformer-8k-v2 | paraformer-8k-v2 | - | - | ¥0.00008/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| paraformer-realtime-8k-v2 | paraformer-realtime-8k-v2 | - | - | ¥0.00024/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| paraformer-realtime-v2 | paraformer-realtime-v2 | - | - | ¥0.00024/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| paraformer-v2 | paraformer-v2 | - | - | ¥0.00008/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qvq-max-2025-03-25 | qvq-max-2025-03-25 | - | - | Input: ¥8 Output: ¥32 | Model: 4.000 Completion: 4.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-coder-turbo-2024-09-19 | qwen-coder-turbo-2024-09-19 | - | - | Input: ¥2 Output: ¥6 | Model: 1.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-coder-turbo-latest | qwen-coder-turbo-latest | - | - | Input: ¥2 Output: ¥6 | Model: 1.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-flash-2025-07-28 | qwen-flash-2025-07-28 | - | - | Input: ¥0.15 Output: ¥1.5 Input 128k 256k: ¥0.6 Input 256k 1m: ¥1.2 Output 128k 256k: ¥6 Output 256k 1m: ¥12 | Model: 0.600 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-flash | qwen-flash | - | - | Input: ¥0.15 Output: ¥1.5 Cache Read: ¥0.015 Cache Read 128k 256k: ¥0.06 Cache Read 256k 1m: ¥0.12 Cache Write: ¥0.188 Cache Write 128k 256k: ¥0.75 Cache Write 256k 1m: ¥1.5 Input 128k 256k: ¥0.6 Input 256k 1m: ¥1.2 Output 128k 256k: ¥6 Output 256k 1m: ¥12 | Model: 0.600 Completion: 10.000 Cache: 0.100 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-image-edit | qwen-image-edit | - | - | ¥0.3/img | Model: 0.300 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-image-plus | qwen-image-plus | - | - | ¥0.2/img | Model: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-image | qwen-image | - | - | ¥0.25/img | Model: 0.250 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-long-latest | qwen-long-latest | - | - | Input: ¥0.5 Output: ¥2 | Model: 0.250 Completion: 4.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-long | qwen-long | - | - | Input: ¥0.5 Output: ¥2 | Model: 0.250 Completion: 4.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-max-latest | qwen-max-latest | - | - | Input: ¥2.4 Output: ¥9.6 | Model: 1.200 Completion: 4.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-max | qwen-max | - | - | Input: ¥2.4 Output: ¥9.6 Cache Read: ¥0.48 | Model: 1.200 Completion: 4.000 Cache: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-mt-image | qwen-mt-image | - | - | ¥0.003/img | Model: 0.003 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-mt-plus | qwen-mt-plus | - | - | Input: ¥1.8 Output: ¥5.4 | Model: 0.900 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-mt-turbo | qwen-mt-turbo | - | - | Input: ¥0.7 Output: ¥1.95 | Model: 0.350 Completion: 2.786 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-omni-turbo-latest | qwen-omni-turbo-latest | - | - | Text Input: ¥0.4 Vision Input: ¥1.5 Audio Input: ¥25 Output: ¥50 Multi Output: ¥50 Multiin Text Output: ¥4.5 Purein Text Output: ¥1.6 | - | - | - | In: text Out: text | - |
| qwen-omni-turbo-realtime-latest | qwen-omni-turbo-realtime-latest | - | - | Text Input: ¥1.6 Vision Input: ¥6 Audio Input: ¥25 Output: ¥50 Multi Output: ¥50 Multiin Text Output: ¥18 Purein Text Output: ¥6.4 | - | - | - | In: text Out: text | - |
| qwen-omni-turbo-realtime | qwen-omni-turbo-realtime | - | - | Text Input: ¥1.6 Vision Input: ¥6 Audio Input: ¥25 Output: ¥50 Multi Output: ¥50 Multiin Text Output: ¥18 Purein Text Output: ¥6.4 | - | - | - | In: text Out: text | - |
| qwen-omni-turbo | qwen-omni-turbo | - | - | Text Input: ¥0.4 Vision Input: ¥1.5 Audio Input: ¥25 Output: ¥50 Audio Input Cache: ¥5 Multi Output: ¥50 Multiin Text Output: ¥4.5 Purein Text Output: ¥1.6 Text Input Cache: ¥0.08 Vision Input Cache: ¥0.3 | - | - | - | In: text Out: text | - |
| qwen-plus-2024-09-19 | qwen-plus-2024-09-19 | - | - | Input: ¥0.8 Output: ¥2 | Model: 0.400 Completion: 2.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-plus-latest | qwen-plus-latest | - | - | Input: ¥0.8 Output: ¥2 Input 128k 256k: ¥2.4 Input 256k 1m: ¥4.8 Output 128k 256k: ¥20 Output 256k 1m: ¥48 Thinking Input: ¥0.8 Thinking Input 128k 256k: ¥2.4 Thinking Input 256k 1m: ¥4.8 Thinking Output: ¥8 Thinking Output 128k 256k: ¥24 Thinking Output 256k 1m: ¥64 | Model: 2.400 Completion: 13.333 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-plus | qwen-plus | - | - | Input: ¥0.8 Output: ¥2 Cache Read: ¥0.08 Cache Read 128k 256k: ¥0.24 Cache Read 256k 1m: ¥0.48 Cache Write: ¥1 Cache Write 128k 256k: ¥3 Cache Write 256k 1m: ¥6 Input 128k 256k: ¥2.4 Input 256k 1m: ¥4.8 Output 128k 256k: ¥20 Output 256k 1m: ¥48 Thinking Cache Read: ¥0.08 Thinking Cache Read 128k 256k: ¥0.24 Thinking Cache Read 256k 1m: ¥0.48 Thinking Cache Write: ¥1 Thinking Cache Write 128k 256k: ¥3 Thinking Cache Write 256k 1m: ¥6 Thinking Input: ¥0.8 Thinking Input 128k 256k: ¥2.4 Thinking Input 256k 1m: ¥4.8 Thinking Output: ¥8 Thinking Output 128k 256k: ¥24 Thinking Output 256k 1m: ¥64 | Model: 2.400 Completion: 13.333 Cache: 0.100 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-turbo-latest | qwen-turbo-latest | - | - | Input: ¥0.3 Output: ¥0.6 Thinking Input: ¥0.3 Thinking Output: ¥3 | Model: 0.150 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-turbo | qwen-turbo | - | - | Input: ¥0.3 Output: ¥0.6 Cache Read: ¥0.06 Thinking Cache Read: ¥0.06 Thinking Input: ¥0.3 Thinking Output: ¥3 | Model: 0.150 Completion: 10.000 Cache: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-vl-max-latest | qwen-vl-max-latest | - | - | Input: ¥1.6 Output: ¥4 | Model: 0.800 Completion: 2.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-vl-max | qwen-vl-max | - | - | Input: ¥1.6 Output: ¥4 Cache Read: ¥0.32 | Model: 0.800 Completion: 2.500 Cache: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-vl-ocr-latest | qwen-vl-ocr-latest | - | - | VL: ¥5/1K | - | - | - | In: text Out: text | - |
| qwen-vl-ocr | qwen-vl-ocr | - | - | VL: ¥5/1K | - | - | - | In: text Out: text | - |
| qwen-vl-plus-latest | qwen-vl-plus-latest | - | - | Input: ¥0.8 Output: ¥2 | Model: 0.400 Completion: 2.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen-vl-plus | qwen-vl-plus | - | - | Input: ¥0.8 Output: ¥2 Cache Read: ¥0.16 | Model: 0.400 Completion: 2.500 Cache: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-14b-instruct-1m | qwen2.5-14b-instruct-1m | - | - | Input: ¥1 Output: ¥3 | Model: 0.500 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-14b-instruct | qwen2.5-14b-instruct | - | - | Input: ¥1 Output: ¥3 | Model: 0.500 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-32b-instruct | qwen2.5-32b-instruct | - | - | Input: ¥2 Output: ¥6 | Model: 1.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-3b-instruct | qwen2.5-3b-instruct | - | - | Input: ¥0.3 Output: ¥0.9 | Model: 0.150 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-72b-instruct | qwen2.5-72b-instruct | - | - | Input: ¥4 Output: ¥12 | Model: 2.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-7b-instruct-1m | qwen2.5-7b-instruct-1m | - | - | Input: ¥0.5 Output: ¥1 | Model: 0.250 Completion: 2.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-7b-instruct | qwen2.5-7b-instruct | - | - | Input: ¥0.5 Output: ¥1 | Model: 0.250 Completion: 2.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-coder-14b-instruct | qwen2.5-coder-14b-instruct | - | - | Input: ¥2 Output: ¥6 | Model: 1.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-coder-32b-instruct | qwen2.5-coder-32b-instruct | - | - | Input: ¥2 Output: ¥6 | Model: 1.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-coder-7b-instruct | qwen2.5-coder-7b-instruct | - | - | Input: ¥1 Output: ¥2 | Model: 0.500 Completion: 2.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-omni-7b | qwen2.5-omni-7b | - | - | Text Input: ¥0.6 Vision Input: ¥2 Audio Input: ¥38 Output: ¥76 Multi Output: ¥76 Multiin Text Output: ¥6 Purein Text Output: ¥2.4 | - | - | - | In: text Out: text | - |
| qwen2.5-vl-32b-instruct | qwen2.5-vl-32b-instruct | - | - | Input: ¥8 Output: ¥24 | Model: 4.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-vl-3b-instruct | qwen2.5-vl-3b-instruct | - | - | Input: ¥1.2 Output: ¥3.6 | Model: 0.600 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-vl-72b-instruct | qwen2.5-vl-72b-instruct | - | - | Input: ¥16 Output: ¥48 | Model: 8.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen2.5-vl-7b-instruct | qwen2.5-vl-7b-instruct | - | - | Input: ¥2 Output: ¥5 | Model: 1.000 Completion: 2.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-0.6b | qwen3-0.6b | - | - | Input: ¥0.3 Output: ¥1.2 Thinking Input: ¥0.3 Thinking Output: ¥3 | Model: 0.150 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-1.7b | qwen3-1.7b | - | - | Input: ¥0.3 Output: ¥1.2 Thinking Input: ¥0.3 Thinking Output: ¥3 | Model: 0.150 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-14b | qwen3-14b | - | - | Input: ¥1 Output: ¥4 Thinking Input: ¥1 Thinking Output: ¥10 | Model: 0.500 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-235b-a22b-instruct-2507 | qwen3-235b-a22b-instruct-2507 | - | - | Input: ¥2 Output: ¥8 | Model: 1.000 Completion: 4.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-235b-a22b-thinking-2507 | qwen3-235b-a22b-thinking-2507 | - | - | Thinking Input: ¥2 Thinking Output: ¥20 | Model: 1.000 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-235b-a22b | qwen3-235b-a22b | - | - | Input: ¥2 Output: ¥8 Thinking Input: ¥2 Thinking Output: ¥20 | Model: 1.000 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-30b-a3b | qwen3-30b-a3b | - | - | Input: ¥0.75 Output: ¥3 Thinking Input: ¥0.75 Thinking Output: ¥7.5 | Model: 0.375 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-32b | qwen3-32b | - | - | Input: ¥2 Output: ¥8 Thinking Input: ¥2 Thinking Output: ¥20 | Model: 1.000 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-4b | qwen3-4b | - | - | Input: ¥0.3 Output: ¥1.2 Thinking Input: ¥0.3 Thinking Output: ¥3 | Model: 0.150 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-8b | qwen3-8b | - | - | Input: ¥0.5 Output: ¥2 Thinking Input: ¥0.5 Thinking Output: ¥5 | Model: 0.250 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-asr-flash-2025-09-08 | qwen3-asr-flash-2025-09-08 | - | - | ¥0.00022/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-asr-flash | qwen3-asr-flash | - | - | ¥0.00022/s | Model: 0.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-coder-30b-a3b-instruct | qwen3-coder-30b-a3b-instruct | - | - | Input: ¥1.5 Output: ¥6 Input 128k 256k: ¥3.75 Input 256k 1m: ¥7.5 Input 32k 128k: ¥2.25 Output 128k 256k: ¥15 Output 256k 1m: ¥37.5 Output 32k 128k: ¥9 | Model: 3.750 Completion: 5.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-coder-480b-a35b-instruct | qwen3-coder-480b-a35b-instruct | - | - | Input: ¥6 Output: ¥24 Input 128k 256k: ¥15 Input 256k 1m: ¥30 Input 32k 128k: ¥9 Output 128k 256k: ¥60 Output 256k 1m: ¥300 Output 32k 128k: ¥36 | Model: 15.000 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-coder-flash | qwen3-coder-flash | - | - | Input: ¥1 Output: ¥4 Cache Read: ¥0.1 Cache Read 128k 256k: ¥0.25 Cache Read 256k 1m: ¥0.5 Cache Read 32k 128k: ¥0.15 Cache Write: ¥1.25 Cache Write 128k 256k: ¥3.125 Cache Write 256k 1m: ¥6.25 Cache Write 32k 128k: ¥1.875 Input 128k 256k: ¥2.5 Input 256k 1m: ¥5 Input 32k 128k: ¥1.5 Output 128k 256k: ¥10 Output 256k 1m: ¥25 Output 32k 128k: ¥6 | Model: 2.500 Completion: 5.000 Cache: 0.100 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-coder-plus-2025-07-22 | qwen3-coder-plus-2025-07-22 | - | - | Input: ¥4 Output: ¥16 Input 128k 256k: ¥10 Input 256k 1m: ¥20 Input 32k 128k: ¥6 Output 128k 256k: ¥40 Output 256k 1m: ¥200 Output 32k 128k: ¥24 | Model: 10.000 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-coder-plus-2025-09-23 | qwen3-coder-plus-2025-09-23 | - | - | Input: ¥4 Output: ¥16 Input 128k 256k: ¥10 Input 256k 1m: ¥20 Input 32k 128k: ¥6 Output 128k 256k: ¥40 Output 256k 1m: ¥200 Output 32k 128k: ¥24 | Model: 10.000 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-coder-plus | qwen3-coder-plus | - | - | Input: ¥4 Output: ¥16 Cache Read: ¥0.4 Cache Read 128k 256k: ¥1 Cache Read 256k 1m: ¥2 Cache Read 32k 128k: ¥0.6 Cache Write: ¥5 Cache Write 128k 256k: ¥12.5 Cache Write 256k 1m: ¥25 Cache Write 32k 128k: ¥7.5 Input 128k 256k: ¥10 Input 256k 1m: ¥20 Input 32k 128k: ¥6 Output 128k 256k: ¥40 Output 256k 1m: ¥200 Output 32k 128k: ¥24 | Model: 10.000 Completion: 10.000 Cache: 0.100 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-max-2025-09-23 | qwen3-max-2025-09-23 | - | - | Input: ¥6 Output: ¥24 Input 128k 256k: ¥15 Input 32k 128k: ¥10 Output 128k 256k: ¥60 Output 32k 128k: ¥40 | Model: 7.500 Completion: 4.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-max-preview | qwen3-max-preview | - | - | Input: ¥6 Output: ¥24 Cache Read: ¥1.2 Cache Read 128k 256k: ¥3 Cache Read 32k 128k: ¥2 Input 128k 256k: ¥15 Input 32k 128k: ¥10 Output 128k 256k: ¥60 Output 32k 128k: ¥40 | Model: 7.500 Completion: 4.000 Cache: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-max | qwen3-max | - | - | Input: ¥6 Output: ¥24 Cache Read: ¥0.6 Cache Read 128k 256k: ¥1.5 Cache Read 32k 128k: ¥1 Cache Write: ¥7.5 Cache Write 128k 256k: ¥18.75 Cache Write 32k 128k: ¥12.5 Input 128k 256k: ¥15 Input 32k 128k: ¥10 Output 128k 256k: ¥60 Output 32k 128k: ¥40 | Model: 7.500 Completion: 4.000 Cache: 0.100 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-omni-30b-a3b-captioner | qwen3-omni-30b-a3b-captioner | - | - | Audio Input: ¥15.8 Multi Output: ¥12.7 Multiin Text Output: ¥12.7 | - | - | - | In: text Out: text | - |
| qwen3-omni-flash-2025-09-15 | qwen3-omni-flash-2025-09-15 | - | - | Text Input: ¥1.8 Vision Input: ¥3.3 Audio Input: ¥15.8 Output: ¥62.6 Multi Output: ¥62.6 Multiin Text Output: ¥12.7 Purein Text Output: ¥6.9 Thinking Audio Input: ¥15.8 Thinking Multiin Text Output: ¥12.7 Thinking Purein Text Output: ¥6.9 Thinking Text Input: ¥1.8 Thinking Vision Input: ¥3.3 | - | - | - | In: text Out: text | - |
| qwen3-omni-flash-realtime-2025-09-15 | qwen3-omni-flash-realtime-2025-09-15 | - | - | Text Input: ¥2.2 Vision Input: ¥3.9 Audio Input: ¥18.9 Output: ¥75.1 Multi Output: ¥75.1 Multiin Text Output: ¥15.2 Purein Text Output: ¥8.3 | - | - | - | In: text Out: text | - |
| qwen3-omni-flash-realtime | qwen3-omni-flash-realtime | - | - | Text Input: ¥2.2 Vision Input: ¥3.9 Audio Input: ¥18.9 Output: ¥75.1 Multi Output: ¥75.1 Multiin Text Output: ¥15.2 Purein Text Output: ¥8.3 | - | - | - | In: text Out: text | - |
| qwen3-omni-flash | qwen3-omni-flash | - | - | Text Input: ¥1.8 Vision Input: ¥3.3 Audio Input: ¥15.8 Output: ¥62.6 Multi Output: ¥62.6 Multiin Text Output: ¥12.7 Purein Text Output: ¥6.9 Thinking Audio Input: ¥15.8 Thinking Multiin Text Output: ¥12.7 Thinking Purein Text Output: ¥6.9 Thinking Text Input: ¥1.8 Thinking Vision Input: ¥3.3 | - | - | - | In: text Out: text | - |
| qwen3-tts-flash-2025-09-18 | qwen3-tts-flash-2025-09-18 | - | - | ¥0.8/10K chars | Model: 0.800 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-tts-flash-realtime-2025-09-18 | qwen3-tts-flash-realtime-2025-09-18 | - | - | ¥1/10K chars | Model: 1.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-tts-flash-realtime | qwen3-tts-flash-realtime | - | - | ¥1/10K chars | Model: 1.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-tts-flash | qwen3-tts-flash | - | - | ¥0.8/10K chars | Model: 0.800 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-vl-plus-2025-09-23 | qwen3-vl-plus-2025-09-23 | - | - | Input: ¥1 Output: ¥10 Input 128k 256k: ¥3 Input 32k 128k: ¥1.5 Output 128k 256k: ¥30 Output 32k 128k: ¥15 | Model: 1.500 Completion: 10.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwen3-vl-plus | qwen3-vl-plus | - | - | Input: ¥1 Output: ¥10 Cache Read: ¥0.2 Cache Read 128k 256k: ¥0.6 Cache Read 32k 128k: ¥0.3 Input 128k 256k: ¥3 Input 32k 128k: ¥1.5 Output 128k 256k: ¥30 Output 32k 128k: ¥15 | Model: 1.500 Completion: 10.000 Cache: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwq-32b-preview | qwq-32b-preview | - | - | Input: ¥2 Output: ¥6 | Model: 1.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwq-32b | qwq-32b | - | - | Input: ¥2 Output: ¥6 | Model: 1.000 Completion: 3.000 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwq-plus-latest | qwq-plus-latest | - | - | Input: ¥1.6 Output: ¥4 | Model: 0.800 Completion: 2.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| qwq-plus | qwq-plus | - | - | Input: ¥1.6 Output: ¥4 | Model: 0.800 Completion: 2.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| text-embedding-async-v2 | text-embedding-async-v2 | - | - | Input: ¥0.7 Output: - | Model: 0.350 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| text-embedding-v1 | text-embedding-v1 | - | - | Input: ¥0.7 Output: - | Model: 0.350 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| text-embedding-v2 | text-embedding-v2 | - | - | Input: ¥0.7 Output: - | Model: 0.350 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| text-embedding-v3 | text-embedding-v3 | - | - | Input: ¥0.5 Output: - | Model: 0.250 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| text-embedding-v4 | text-embedding-v4 | - | - | Input: ¥0.5 Output: - | Model: 0.250 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| tongyi-embedding-vision-flash | tongyi-embedding-vision-flash | - | - | Text: ¥0.2/1K Image: ¥0.5/1K | - | - | - | In: text Out: text | - |
| tongyi-embedding-vision-plus | tongyi-embedding-vision-plus | - | - | Text: ¥0.5/1K Image: ¥0.5/1K | - | - | - | In: text Out: text | - |
| tongyi-intent-detect-v3 | tongyi-intent-detect-v3 | - | - | Input: ¥0.4 Output: ¥1 | Model: 0.200 Completion: 2.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-animate-mix | wan2.2-animate-mix | - | - | Per Second Pro: ¥0.9 Per Second Standard: ¥0.6 | Model: 0.600 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-animate-move | wan2.2-animate-move | - | - | Per Second Pro: ¥0.6 Per Second Standard: ¥0.4 | Model: 0.400 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-i2v-flash | wan2.2-i2v-flash | - | - | Per Second 1080p: ¥0.48 Per Second 480p: ¥0.1 Per Second 720p: ¥0.2 | Model: 0.100 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-i2v-plus | wan2.2-i2v-plus | - | - | Per Second 1080p: ¥0.7 Per Second 480p: ¥0.14 | Model: 0.140 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-kf2v-flash | wan2.2-kf2v-flash | - | - | Per Second 1080p: ¥0.48 Per Second 480p: ¥0.1 Per Second 720p: ¥0.2 | Model: 0.100 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-s2v | wan2.2-s2v | - | - | Per Second 480p: ¥0.5 Per Second 720p: ¥0.9 | Model: 0.500 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-t2i-flash | wan2.2-t2i-flash | - | - | ¥0.14/img | Model: 0.140 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-t2i-plus | wan2.2-t2i-plus | - | - | ¥0.2/img | Model: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.2-t2v-plus | wan2.2-t2v-plus | - | - | Per Second 1080x1920: ¥0.7 Per Second 1248x1632: ¥0.7 Per Second 1440x1440: ¥0.7 Per Second 1632x1248: ¥0.7 Per Second 1920x1080: ¥0.7 Per Second 480x832: ¥0.14 Per Second 624x624: ¥0.14 Per Second 832x480: ¥0.14 | Model: 0.140 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.5-i2i-preview | wan2.5-i2i-preview | - | - | ¥0.2/img | Model: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.5-i2v-preview | wan2.5-i2v-preview | - | - | Per Second 1080p: ¥1 Per Second 480p: ¥0.3 Per Second 720p: ¥0.6 | Model: 0.300 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.5-t2i-preview | wan2.5-t2i-preview | - | - | ¥0.2/img | Model: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wan2.5-t2v-preview | wan2.5-t2v-preview | - | - | Per Second 1080x1920: ¥1 Per Second 1088x832: ¥0.6 Per Second 1248x1632: ¥1 Per Second 1280x720: ¥0.6 Per Second 1440x1440: ¥1 Per Second 1632x1248: ¥1 Per Second 1920x1080: ¥1 Per Second 480x832: ¥0.3 Per Second 624x624: ¥0.3 Per Second 720x1280: ¥0.6 Per Second 832x1088: ¥0.6 Per Second 832x480: ¥0.3 Per Second 960x960: ¥0.6 | Model: 0.300 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx-background-generation-v2 | wanx-background-generation-v2 | - | - | ¥0.08/img | Model: 0.080 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx-sketch-to-image-lite | wanx-sketch-to-image-lite | - | - | ¥0.06/img | Model: 0.060 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx-style-repaint-v1 | wanx-style-repaint-v1 | - | - | ¥0.12/img | Model: 0.120 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx-v1 | wanx-v1 | - | - | ¥0.16/img | Model: 0.160 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.0-t2i-turbo | wanx2.0-t2i-turbo | - | - | ¥0.04/img | Model: 0.040 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-i2v-plus | wanx2.1-i2v-plus | - | - | Per Second Standard: ¥0.7 | Model: 0.700 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-i2v-turbo | wanx2.1-i2v-turbo | - | - | Per Second Standard: ¥0.24 | Model: 0.240 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-imageedit | wanx2.1-imageedit | - | - | ¥0.14/img | Model: 0.140 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-kf2v-plus | wanx2.1-kf2v-plus | - | - | Per Second Standard: ¥0.7 | Model: 0.700 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-t2i-plus | wanx2.1-t2i-plus | - | - | ¥0.2/img | Model: 0.200 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-t2i-turbo | wanx2.1-t2i-turbo | - | - | ¥0.14/img | Model: 0.140 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-t2v-plus | wanx2.1-t2v-plus | - | - | Per Second 1088x832: ¥0.7 Per Second 1280x720: ¥0.7 Per Second 720x1280: ¥0.7 Per Second 832x1088: ¥0.7 Per Second 960x960: ¥0.7 | Model: 0.700 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-t2v-turbo | wanx2.1-t2v-turbo | - | - | Per Second 1088x832: ¥0.24 Per Second 1280x720: ¥0.24 Per Second 480x832: ¥0.24 Per Second 624x624: ¥0.24 Per Second 720x1280: ¥0.24 Per Second 832x1088: ¥0.24 Per Second 832x480: ¥0.24 Per Second 960x960: ¥0.24 | Model: 0.240 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
| wanx2.1-vace-plus | wanx2.1-vace-plus | - | - | Per Second Standard: ¥0.7 | Model: 0.700 (CNY pricing, multiply by USD/CNY rate for NewAPI) | - | - | In: text Out: text | - |
Amazon Bedrock¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek-R1 | deepseek.r1-v1:0 | 128K | 32.8K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-01-20 Updated: 2025-05-29 |
| Llama 3.1 70B Instruct | meta.llama3-1-70b-instruct-v1:0 | 128K | 4.1K | Input: $0.72 Output: $0.72 | Model: 0.360 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Claude Instant | anthropic.claude-instant-v1 | 100K | 4.1K | Input: $0.8 Output: $2.4 | Model: 0.400 Completion: 3.000 | 🌡️ | 2023-08 | In: text Out: text | Released: 2023-03-01 |
| Titan Text G1 - Express | amazon.titan-text-express-v1 | 128K | 4.1K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| Qwen3 Coder 480B A35B Instruct | qwen.qwen3-coder-480b-a35b-v1:0 | 131.1K | 65.5K | Input: $0.22 Output: $1.8 | Model: 0.110 Completion: 8.182 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2025-09-18 |
| Claude Sonnet 4.6 (EU) | eu.anthropic.claude-sonnet-4-6 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Command R | cohere.command-r-v1:0 | 128K | 4.1K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-03-11 |
| Claude Haiku 4.5 (EU) | eu.anthropic.claude-haiku-4-5-20251001-v1:0 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| gpt-oss-120b | openai.gpt-oss-120b-1:0 | 128K | 4.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| Claude Opus 4 (US) | us.anthropic.claude-opus-4-20250514-v1:0 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| NVIDIA Nemotron Nano 12B v2 VL BF16 | nvidia.nemotron-nano-12b-v2 | 128K | 4.1K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-12-01 |
| Claude Sonnet 3.7 | anthropic.claude-3-7-sonnet-20250219-v1:0 | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Sonnet 4.6 | anthropic.claude-sonnet-4-6 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| MiniMax M2.1 | minimax.minimax-m2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| Claude Opus 4.5 (Global) | global.anthropic.claude-opus-4-5-20251101-v1:0 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 Updated: 2025-08-01 |
| Ministral 3 8B | mistral.ministral-3-8b-instruct | 128K | 4.1K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| GPT OSS Safeguard 20B | openai.gpt-oss-safeguard-20b | 128K | 4.1K | Input: $0.07 Output: $0.2 | Model: 0.035 Completion: 2.857 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| Nova Lite | amazon.nova-lite-v1:0 | 300K | 8.2K | Input: $0.06 Output: $0.24 Cache Read: $0.015 | Model: 0.030 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Released: 2024-12-03 |
| Claude Sonnet 4.5 (EU) | eu.anthropic.claude-sonnet-4-5-20250929-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Google Gemma 3 12B | google.gemma-3-12b-it | 131.1K | 8.2K | Input: $0.049999999999999996 Output: $0.09999999999999999 | Model: 0.025 Completion: 2.000 | 🌡️ | 2024-12 | In: text, image Out: text | Released: 2024-12-01 |
| Llama 3.1 8B Instruct | meta.llama3-1-8b-instruct-v1:0 | 128K | 4.1K | Input: $0.22 Output: $0.22 | Model: 0.110 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Claude Sonnet 4.5 | anthropic.claude-sonnet-4-5-20250929-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Llama 4 Maverick 17B Instruct | meta.llama4-maverick-17b-instruct-v1:0 | 1M | 16.4K | Input: $0.24 Output: $0.97 | Model: 0.120 Completion: 4.042 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Ministral 14B 3.0 | mistral.ministral-3-14b-instruct | 128K | 4.1K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| MiniMax M2 | minimax.minimax-m2 | 204.6K | 128K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-27 |
| Mistral-7B-Instruct-v0.3 | mistral.mistral-7b-instruct-v0:2 | 127K | 127K | Input: $0.11 Output: $0.11 | Model: 0.055 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-01 |
| Nova Micro | amazon.nova-micro-v1:0 | 128K | 8.2K | Input: $0.035 Output: $0.14 Cache Read: $0.00875 | Model: 0.018 Completion: 4.000 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12-03 |
| Claude Sonnet 3.5 v2 | anthropic.claude-3-5-sonnet-20241022-v2:0 | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| DeepSeek-V3.2 | deepseek.v3.2-v1:0 | 163.8K | 81.9K | Input: $0.62 Output: $1.85 | Model: 0.310 Completion: 2.984 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2026-02-15 |
| Claude Sonnet 4 | anthropic.claude-sonnet-4-20250514-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Qwen/Qwen3-VL-235B-A22B-Instruct | qwen.qwen3-vl-235b-a22b | 262K | 262K | Input: $0.3 Output: $1.5 | Model: 0.150 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Claude Opus 4.6 (Global) | global.anthropic.claude-opus-4-6-v1 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Palmyra X4 | writer.palmyra-x4-v1:0 | 122.9K | 8.2K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-28 |
| Mixtral-8x7B-Instruct-v0.1 | mistral.mixtral-8x7b-instruct-v0:1 | 32K | 32K | Input: $0.7 Output: $0.7 | Model: 0.350 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-01 |
| Nova Pro | amazon.nova-pro-v1:0 | 300K | 8.2K | Input: $0.8 Output: $3.2 Cache Read: $0.2 | Model: 0.400 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Released: 2024-12-03 |
| Claude Opus 4.5 (US) | us.anthropic.claude-opus-4-5-20251101-v1:0 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 Updated: 2025-08-01 |
| Llama 3.2 90B Instruct | meta.llama3-2-90b-instruct-v1:0 | 128K | 4.1K | Input: $0.72 Output: $0.72 | Model: 0.360 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Claude Opus 4.6 (US) | us.anthropic.claude-opus-4-6-v1 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Gemma 3 4B IT | google.gemma-3-4b-it | 128K | 4.1K | Input: $0.04 Output: $0.08 | Model: 0.020 Completion: 2.000 | 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-12-01 |
| Claude Opus 4.6 | anthropic.claude-opus-4-6-v1 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Titan Text G1 - Express | amazon.titan-text-express-v1:0:8k | 128K | 4.1K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| GLM-4.7-Flash | zai.glm-4.7-flash | 200K | 131.1K | Input: $0.07 Output: $0.4 | Model: 0.035 Completion: 5.714 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-01-19 |
| Claude Opus 4 | anthropic.claude-opus-4-20250514-v1:0 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude 2 | anthropic.claude-v2 | 100K | 4.1K | Input: $8 Output: $24 | Model: 4.000 Completion: 3.000 | 🌡️ | 2023-08 | In: text Out: text | Released: 2023-07-11 |
| Claude Sonnet 3 | anthropic.claude-3-sonnet-20240229-v1:0 | 200K | 4.1K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🔧 🌡️ | 2023-08 | In: text, image, pdf Out: text | Released: 2024-03-04 |
| Claude Sonnet 4.6 (Global) | global.anthropic.claude-sonnet-4-6 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Llama 3.2 1B Instruct | meta.llama3-2-1b-instruct-v1:0 | 131K | 4.1K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-09-25 |
| Claude Opus 4.1 | anthropic.claude-opus-4-1-20250805-v1:0 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Llama 4 Scout 17B Instruct | meta.llama4-scout-17b-instruct-v1:0 | 3.5M | 16.4K | Input: $0.17 Output: $0.66 | Model: 0.085 Completion: 3.882 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Claude 2.1 | anthropic.claude-v2:1 | 200K | 4.1K | Input: $8 Output: $24 | Model: 4.000 Completion: 3.000 | 🌡️ | 2023-08 | In: text Out: text | Released: 2023-11-21 |
| Mistral Large (24.02) | mistral.mistral-large-2402-v1:0 | 128K | 4.1K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| DeepSeek-V3.1 | deepseek.v3-v1:0 | 163.8K | 81.9K | Input: $0.58 Output: $1.68 | Model: 0.290 Completion: 2.897 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-09-18 |
| Command R+ | cohere.command-r-plus-v1:0 | 128K | 4.1K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-04-04 |
| Claude Haiku 4.5 (Global) | global.anthropic.claude-haiku-4-5-20251001-v1:0 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| NVIDIA Nemotron Nano 9B v2 | nvidia.nemotron-nano-9b-v2 | 128K | 4.1K | Input: $0.06 Output: $0.23 | Model: 0.030 Completion: 3.833 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| Palmyra X5 | writer.palmyra-x5-v1:0 | 1M | 8.2K | Input: $0.6 Output: $6 | Model: 0.300 Completion: 10.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-28 |
| Llama 3.3 70B Instruct | meta.llama3-3-70b-instruct-v1:0 | 128K | 4.1K | Input: $0.72 Output: $0.72 | Model: 0.360 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| GLM-4.7 | zai.glm-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| Kimi K2 Thinking | moonshot.kimi-k2-thinking | 256K | 256K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-02 |
| Claude Haiku 3 | anthropic.claude-3-haiku-20240307-v1:0 | 200K | 4.1K | Input: $0.25 Output: $1.25 | Model: 0.125 Completion: 5.000 | 📎 🔧 🌡️ | 2024-02 | In: text, image, pdf Out: text | Released: 2024-03-13 |
| Claude Sonnet 4.5 (US) | us.anthropic.claude-sonnet-4-5-20250929-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Llama 3 8B Instruct | meta.llama3-8b-instruct-v1:0 | 8.2K | 2K | Input: $0.3 Output: $0.6 | Model: 0.150 Completion: 2.000 | 🌡️ | 2023-03 | In: text Out: text | Open Weights Released: 2024-07-23 |
| gpt-oss-20b | openai.gpt-oss-20b-1:0 | 128K | 4.1K | Input: $0.07 Output: $0.3 | Model: 0.035 Completion: 4.286 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| Claude Sonnet 4.6 (US) | us.anthropic.claude-sonnet-4-6 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Llama 3.2 11B Instruct | meta.llama3-2-11b-instruct-v1:0 | 128K | 4.1K | Input: $0.16 Output: $0.16 | Model: 0.080 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Claude Opus 4.5 (EU) | eu.anthropic.claude-opus-4-5-20251101-v1:0 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 Updated: 2025-08-01 |
| Command | cohere.command-text-v14 | 4.1K | 4.1K | Input: $1.5 Output: $2 | Model: 0.750 Completion: 1.333 | 🌡️ | 2023-08 | In: text Out: text | Open Weights Released: 2023-11-01 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | qwen.qwen3-next-80b-a3b | 262K | 262K | Input: $0.14 Output: $1.4 | Model: 0.070 Completion: 10.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-18 Updated: 2025-11-25 |
| Claude Sonnet 4 (US) | us.anthropic.claude-sonnet-4-20250514-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Jamba 1.5 Mini | ai21.jamba-1-5-mini-v1:0 | 256K | 4.1K | Input: $0.2 Output: $0.4 | Model: 0.100 Completion: 2.000 | 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2024-08-15 |
| Llama 3 70B Instruct | meta.llama3-70b-instruct-v1:0 | 8.2K | 2K | Input: $2.65 Output: $3.5 | Model: 1.325 Completion: 1.321 | 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Jamba 1.5 Large | ai21.jamba-1-5-large-v1:0 | 256K | 4.1K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2024-08-15 |
| Qwen3 Coder 30B A3B Instruct | qwen.qwen3-coder-30b-a3b-v1:0 | 262.1K | 131.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2025-09-18 |
| Claude Opus 3 | anthropic.claude-3-opus-20240229-v1:0 | 200K | 4.1K | Input: $15 Output: $75 | Model: 7.500 Completion: 5.000 | 📎 🔧 🌡️ | 2023-08 | In: text, image, pdf Out: text | Released: 2024-02-29 |
| Claude Haiku 4.5 (US) | us.anthropic.claude-haiku-4-5-20251001-v1:0 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Qwen3 235B A22B 2507 | qwen.qwen3-235b-a22b-2507-v1:0 | 262.1K | 131.1K | Input: $0.22 Output: $0.88 | Model: 0.110 Completion: 4.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2025-09-18 |
| GPT OSS Safeguard 120B | openai.gpt-oss-safeguard-120b | 128K | 4.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-01 |
| Claude Sonnet 3.5 | anthropic.claude-3-5-sonnet-20240620-v1:0 | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2024-06-20 |
| Voxtral Small 24B 2507 | mistral.voxtral-small-24b-2507 | 32K | 8.2K | Input: $0.15 Output: $0.35 | Model: 0.075 Completion: 2.333 | 📎 🔧 🌡️ | - | In: text, audio Out: text | Open Weights Released: 2025-07-01 |
| Command Light | cohere.command-light-text-v14 | 4.1K | 4.1K | Input: $0.3 Output: $0.6 | Model: 0.150 Completion: 2.000 | 🌡️ | 2023-08 | In: text Out: text | Open Weights Released: 2023-11-01 |
| Claude Haiku 4.5 | anthropic.claude-haiku-4-5-20251001-v1:0 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Llama 3.2 3B Instruct | meta.llama3-2-3b-instruct-v1:0 | 131K | 4.1K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-09-25 |
| Google Gemma 3 27B Instruct | google.gemma-3-27b-it | 202.8K | 8.2K | Input: $0.12 Output: $0.2 | Model: 0.060 Completion: 1.667 | 📎 🔧 🌡️ | 2025-07 | In: text, image Out: text | Open Weights Released: 2025-07-27 |
| Claude Opus 4.1 (US) | us.anthropic.claude-opus-4-1-20250805-v1:0 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude Sonnet 4 (Global) | global.anthropic.claude-sonnet-4-20250514-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Haiku 3.5 | anthropic.claude-3-5-haiku-20241022-v1:0 | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Sonnet 4 (EU) | eu.anthropic.claude-sonnet-4-20250514-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Opus 4.5 | anthropic.claude-opus-4-5-20251101-v1:0 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 Updated: 2025-08-01 |
| Claude Opus 4.6 (EU) | eu.anthropic.claude-opus-4-6-v1 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Nova Premier | amazon.nova-premier-v1:0 | 1M | 16.4K | Input: $2.5 Output: $12.5 | Model: 1.250 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Released: 2024-12-03 |
| Nova 2 Lite | amazon.nova-2-lite-v1:0 | 128K | 4.1K | Input: $0.33 Output: $2.75 | Model: 0.165 Completion: 8.333 | 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2024-12-01 |
| Qwen3 32B (dense) | qwen.qwen3-32b-v1:0 | 16.4K | 16.4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2025-09-18 |
| Kimi K2.5 | moonshotai.kimi-k2.5 | 256K | 256K | Input: $0.6 Output: $3 | Model: 0.300 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-02-06 |
| Voxtral Mini 3B 2507 | mistral.voxtral-mini-3b-2507 | 128K | 4.1K | Input: $0.04 Output: $0.04 | Model: 0.020 Completion: 1.000 | 🔧 🌡️ | - | In: audio, text Out: text | Released: 2024-12-01 |
| Claude Sonnet 4.5 (Global) | global.anthropic.claude-sonnet-4-5-20250929-v1:0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
Anthropic¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.5 | claude-opus-4-5-20251101 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-01 |
| Claude Haiku 3.5 (latest) | claude-3-5-haiku-latest | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Opus 4.1 (latest) | claude-opus-4-1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude Sonnet 3.5 v2 | claude-3-5-sonnet-20241022 | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04-30 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Sonnet 3 | claude-3-sonnet-20240229 | 200K | 4.1K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $0.3 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-03-04 |
| Claude Opus 4.6 | claude-opus-4-6 | 200K | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Claude Sonnet 4 (latest) | claude-sonnet-4-0 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Opus 4 | claude-opus-4-20250514 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 4.5 | claude-sonnet-4-5-20250929 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Claude Opus 4 (latest) | claude-opus-4-0 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Haiku 3.5 | claude-3-5-haiku-20241022 | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Sonnet 3.5 | claude-3-5-sonnet-20240620 | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04-30 | In: text, image, pdf Out: text | Released: 2024-06-20 |
| Claude Sonnet 3.7 (latest) | claude-3-7-sonnet-latest | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-31 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Sonnet 3.7 | claude-3-7-sonnet-20250219 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-31 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Haiku 3 | claude-3-haiku-20240307 | 200K | 4.1K | Input: $0.25 Output: $1.25 Cache Read: $0.03 Cache Write: $0.3 | Model: 0.125 Completion: 5.000 Cache: 0.120 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-03-13 |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Haiku 4.5 (latest) | claude-haiku-4-5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Opus 4.5 (latest) | claude-opus-4-5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Claude Opus 3 | claude-3-opus-20240229 | 200K | 4.1K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-02-29 |
| Claude Sonnet 4.5 (latest) | claude-sonnet-4-5 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Claude Sonnet 4 | claude-sonnet-4-20250514 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Opus 4.1 | claude-opus-4-1-20250805 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
Azure¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5-Codex | gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| GPT-5 Pro | gpt-5-pro | 400K | 272K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-10-06 |
| Phi-3-small-instruct (128k) | phi-3-small-128k-instruct | 128K | 4.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| GPT-4o mini | gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.08 | Model: 0.075 Completion: 4.000 Cache: 0.533 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-07-18 |
| text-embedding-ada-002 | text-embedding-ada-002 | 8.2K | 1.5K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Released: 2022-12-15 |
| Grok 4 Fast (Reasoning) | grok-4-fast-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-09-19 |
| GPT-5.1 Codex Max | gpt-5.1-codex-max | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Phi-3-medium-instruct (128k) | phi-3-medium-128k-instruct | 128K | 4.1K | Input: $0.17 Output: $0.68 | Model: 0.085 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Phi-4-multimodal | phi-4-multimodal | 128K | 4.1K | Input: $0.08 Output: $0.32 Input Audio: $4 | Model: 2.000 Completion: 0.080 | 📎 🌡️ | 2023-10 | In: text, image, audio Out: text | Open Weights Released: 2024-12-11 |
| MAI-DS-R1 | mai-ds-r1 | 128K | 8.2K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🌡️ | 2024-06 | In: text Out: text | Released: 2025-01-20 |
| Claude Opus 4.1 | claude-opus-4-1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-18 |
| Phi-3.5-MoE-instruct | phi-3.5-moe-instruct | 128K | 4.1K | Input: $0.16 Output: $0.64 | Model: 0.080 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-08-20 |
| GPT-4 Turbo Vision | gpt-4-turbo-vision | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | 2023-11 | In: text, image Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| Ministral 3B | ministral-3b | 128K | 8.2K | Input: $0.04 Output: $0.04 | Model: 0.020 Completion: 1.000 | 🔧 🌡️ | 2024-03 | In: text Out: text | Open Weights Released: 2024-10-22 |
| GPT-5.2 Codex | gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2026-01-14 |
| Grok 3 | grok-3 | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Claude Opus 4.6 | claude-opus-4-6 | 200K | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Llama-3.2-90B-Vision-Instruct | llama-3.2-90b-vision-instruct | 128K | 8.2K | Input: $2.04 Output: $2.04 | Model: 1.020 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Grok Code Fast 1 | grok-code-fast-1 | 256K | 10K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Released: 2025-08-28 |
| Llama-3.3-70B-Instruct | llama-3.3-70b-instruct | 128K | 32.8K | Input: $0.71 Output: $0.71 | Model: 0.355 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Phi-3.5-mini-instruct | phi-3.5-mini-instruct | 128K | 4.1K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-08-20 |
| Command A | cohere-command-a | 256K | 8K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2025-03-13 |
| Mistral Medium 3 | mistral-medium-2505 | 128K | 128K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-05-07 |
| DeepSeek-V3.1 | deepseek-v3.1 | 131.1K | 131.1K | Input: $0.56 Output: $1.68 | Model: 0.280 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-08-21 |
| o1 | o1 | 200K | 100K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2023-09 | In: text, image Out: text | Released: 2024-12-05 |
| GPT-5.1 | gpt-5.1 | 272K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image, audio Out: text, image, audio | Released: 2025-11-14 |
| Llama 4 Scout 17B 16E Instruct | llama-4-scout-17b-16e-instruct | 128K | 8.2K | Input: $0.2 Output: $0.78 | Model: 0.100 Completion: 3.900 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Meta-Llama-3.1-405B-Instruct | meta-llama-3.1-405b-instruct | 128K | 32.8K | Input: $5.33 Output: $16 | Model: 2.665 Completion: 3.002 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Command R+ | cohere-command-r-plus-08-2024 | 128K | 4K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2024-08-30 |
| GPT-5.2 Chat | gpt-5.2-chat | 128K | 16.4K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-5 Chat | gpt-5-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 | 2024-10-24 | In: text, image Out: text | Released: 2025-08-07 |
| Grok 4 | grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 Reasoning: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-09 |
| GPT-5.1 Chat | gpt-5.1-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image, audio Out: text, image, audio | Released: 2025-11-14 |
| Meta-Llama-3-8B-Instruct | meta-llama-3-8b-instruct | 8.2K | 2K | Input: $0.3 Output: $0.61 | Model: 0.150 Completion: 2.033 | 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-04-18 |
| o3 | o3 | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| Llama-3.2-11B-Vision-Instruct | llama-3.2-11b-vision-instruct | 128K | 8.2K | Input: $0.37 Output: $0.37 | Model: 0.185 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Meta-Llama-3-70B-Instruct | meta-llama-3-70b-instruct | 8.2K | 2K | Input: $2.68 Output: $3.54 | Model: 1.340 Completion: 1.321 | 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-04-18 |
| DeepSeek-R1-0528 | deepseek-r1-0528 | 163.8K | 163.8K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-05-28 |
| GPT-3.5 Turbo 0301 | gpt-3.5-turbo-0301 | 4.1K | 4.1K | Input: $1.5 Output: $2 | Model: 0.750 Completion: 1.333 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-03-01 |
| text-embedding-3-small | text-embedding-3-small | 8.2K | 1.5K | Input: $0.02 Output: $0 | Model: 0.010 | - | - | In: text Out: text | Released: 2024-01-25 |
| DeepSeek-R1 | deepseek-r1 | 163.8K | 163.8K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-01-20 |
| Phi-4-mini | phi-4-mini | 128K | 4.1K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| DeepSeek-V3.2-Speciale | deepseek-v3.2-speciale | 128K | 128K | Input: $0.58 Output: $1.68 | Model: 0.290 Completion: 2.897 | 🧠 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| GPT-4.1 nano | gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 Cache Read: $0.03 | Model: 0.050 Completion: 4.000 Cache: 0.300 | 📎 🔧 🌡️ | 2024-05 | In: text, image Out: text | Released: 2025-04-14 |
| Command R | cohere-command-r-08-2024 | 128K | 4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2024-08-30 |
| GPT-3.5 Turbo 0613 | gpt-3.5-turbo-0613 | 16.4K | 16.4K | Input: $3 Output: $4 | Model: 1.500 Completion: 1.333 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-06-13 |
| text-embedding-3-large | text-embedding-3-large | 8.2K | 3.1K | Input: $0.13 Output: $0 | Model: 0.065 | - | - | In: text Out: text | Released: 2024-01-25 |
| GPT-5.1 Codex Mini | gpt-5.1-codex-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-14 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.125 | Model: 0.875 Completion: 8.000 Cache: 0.071 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| Kimi K2.5 | kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 | Model: 0.300 Completion: 5.000 | 🧠 🔧 🌡️ | 2025-01 | In: text, image Out: text | Open Weights Released: 2026-02-06 |
| DeepSeek-V3-0324 | deepseek-v3-0324 | 131.1K | 131.1K | Input: $1.14 Output: $4.56 | Model: 0.570 Completion: 4.000 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-03-24 |
| Model Router | model-router | 128K | 16.4K | Input: $0.14 Output: $0 | Model: 0.070 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-05-19 Updated: 2025-11-18 |
| GPT-4.1 | gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-05 | In: text, image Out: text | Released: 2025-04-14 |
| GPT-4 Turbo | gpt-4-turbo | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | 2023-11 | In: text, image Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| Mistral Nemo | mistral-nemo | 128K | 128K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2024-07-18 |
| DeepSeek-V3.2 | deepseek-v3.2 | 128K | 128K | Input: $0.58 Output: $1.68 | Model: 0.290 Completion: 2.897 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| Embed v4 | cohere-embed-v-4-0 | 128K | 1.5K | Input: $0.12 Output: $0 | Model: 0.060 | 📎 | - | In: text, image Out: text | Open Weights Released: 2025-04-15 |
| Grok 3 Mini | grok-3-mini | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 Reasoning: $0.5 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| GPT-4 32K | gpt-4-32k | 32.8K | 32.8K | Input: $60 Output: $120 | Model: 30.000 Completion: 2.000 | 🔧 🌡️ | 2023-11 | In: text Out: text | Released: 2023-03-14 |
| GPT-5 | gpt-5 | 272K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| o4-mini | o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.28 | Model: 0.550 Completion: 4.000 Cache: 0.255 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| Phi-4 | phi-4 | 128K | 4.1K | Input: $0.125 Output: $0.5 | Model: 0.063 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| GPT-4.1 mini | gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-05 | In: text, image Out: text | Released: 2025-04-14 |
| Phi-4-reasoning-plus | phi-4-reasoning-plus | 32K | 4.1K | Input: $0.125 Output: $0.5 | Model: 0.063 Completion: 4.000 | 🧠 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| Kimi K2 Thinking | kimi-k2-thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 Updated: 2025-12-02 |
| Codex Mini | codex-mini | 200K | 100K | Input: $1.5 Output: $6 Cache Read: $0.375 | Model: 0.750 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-04 | In: text Out: text | Released: 2025-05-16 |
| Phi-3-mini-instruct (4k) | phi-3-mini-4k-instruct | 4.1K | 1K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Meta-Llama-3.1-70B-Instruct | meta-llama-3.1-70b-instruct | 128K | 32.8K | Input: $2.68 Output: $3.54 | Model: 1.340 Completion: 1.321 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| o1-preview | o1-preview | 128K | 32.8K | Input: $16.5 Output: $66 Cache Read: $8.25 | Model: 8.250 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2023-09 | In: text Out: text | Released: 2024-09-12 |
| Meta-Llama-3.1-8B-Instruct | meta-llama-3.1-8b-instruct | 128K | 32.8K | Input: $0.3 Output: $0.61 | Model: 0.150 Completion: 2.033 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-31 | In: text, image, pdf Out: text | Released: 2025-11-18 |
| GPT-5.1 Codex | gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image, audio Out: text, image, audio | Released: 2025-11-14 |
| Mistral Large 24.11 | mistral-large-2411 | 128K | 32.8K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | 2024-09 | In: text Out: text | Released: 2024-11-01 |
| Claude Opus 4.5 | claude-opus-4-5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 Updated: 2025-08-01 |
| Phi-4-mini-reasoning | phi-4-mini-reasoning | 128K | 4.1K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| GPT-3.5 Turbo 0125 | gpt-3.5-turbo-0125 | 16.4K | 16.4K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🌡️ | 2021-08 | In: text Out: text | Released: 2024-01-25 |
| Embed v3 Multilingual | cohere-embed-v3-multilingual | 512 | 1K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Open Weights Released: 2023-11-07 |
| Phi-3-medium-instruct (4k) | phi-3-medium-4k-instruct | 4.1K | 1K | Input: $0.17 Output: $0.68 | Model: 0.085 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Embed v3 English | cohere-embed-v3-english | 512 | 1K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Open Weights Released: 2023-11-07 |
| o3-mini | o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2024-05 | In: text Out: text | Released: 2024-12-20 Updated: 2025-01-29 |
| Grok 4 Fast (Non-Reasoning) | grok-4-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-09-19 |
| Llama 4 Maverick 17B 128E Instruct FP8 | llama-4-maverick-17b-128e-instruct-fp8 | 128K | 8.2K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-11-18 |
| GPT-5 Mini | gpt-5-mini | 272K | 128K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| Phi-3-mini-instruct (128k) | phi-3-mini-128k-instruct | 128K | 4.1K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Phi-4-reasoning | phi-4-reasoning | 32K | 4.1K | Input: $0.125 Output: $0.5 | Model: 0.063 Completion: 4.000 | 🧠 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| GPT-3.5 Turbo 1106 | gpt-3.5-turbo-1106 | 16.4K | 16.4K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-11-06 |
| GPT-4 | gpt-4 | 8.2K | 8.2K | Input: $60 Output: $120 | Model: 30.000 Completion: 2.000 | 🔧 🌡️ | 2023-11 | In: text Out: text | Released: 2023-03-14 |
| GPT-5 Nano | gpt-5-nano | 272K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.01 | Model: 0.025 Completion: 8.000 Cache: 0.200 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-3.5 Turbo Instruct | gpt-3.5-turbo-instruct | 4.1K | 4.1K | Input: $1.5 Output: $2 | Model: 0.750 Completion: 1.333 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-09-21 |
| o1-mini | o1-mini | 128K | 65.5K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2023-09 | In: text Out: text | Released: 2024-09-12 |
| Mistral Small 3.1 | mistral-small-2503 | 128K | 32.8K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 📎 🔧 🌡️ | 2024-09 | In: text, image Out: text | Released: 2025-03-01 |
| Codestral 25.01 | codestral-2501 | 256K | 256K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2025-01-01 |
| GPT-4o | gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 |
| Phi-3-small-instruct (8k) | phi-3-small-8k-instruct | 8.2K | 2K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
Azure Cognitive Services¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.1 | claude-opus-4-1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-18 |
| Claude Opus 4.6 | claude-opus-4-6 | 200K | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-31 | In: text, image, pdf Out: text | Released: 2025-11-18 |
| Claude Opus 4.5 | claude-opus-4-5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 Updated: 2025-08-01 |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-11-18 |
| Phi-3-small-instruct (8k) | phi-3-small-8k-instruct | 8.2K | 2K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| GPT-4o | gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 |
| Codestral 25.01 | codestral-2501 | 256K | 256K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2025-01-01 |
| Mistral Small 3.1 | mistral-small-2503 | 128K | 32.8K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 📎 🔧 🌡️ | 2024-09 | In: text, image Out: text | Released: 2025-03-01 |
| o1-mini | o1-mini | 128K | 65.5K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2023-09 | In: text Out: text | Released: 2024-09-12 |
| GPT-3.5 Turbo Instruct | gpt-3.5-turbo-instruct | 4.1K | 4.1K | Input: $1.5 Output: $2 | Model: 0.750 Completion: 1.333 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-09-21 |
| GPT-5 Nano | gpt-5-nano | 272K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.01 | Model: 0.025 Completion: 8.000 Cache: 0.200 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-4 | gpt-4 | 8.2K | 8.2K | Input: $60 Output: $120 | Model: 30.000 Completion: 2.000 | 🔧 🌡️ | 2023-11 | In: text Out: text | Released: 2023-03-14 |
| GPT-3.5 Turbo 1106 | gpt-3.5-turbo-1106 | 16.4K | 16.4K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-11-06 |
| Phi-4-reasoning | phi-4-reasoning | 32K | 4.1K | Input: $0.125 Output: $0.5 | Model: 0.063 Completion: 4.000 | 🧠 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| Phi-3-mini-instruct (128k) | phi-3-mini-128k-instruct | 128K | 4.1K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| GPT-5 Mini | gpt-5-mini | 272K | 128K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| Llama 4 Maverick 17B 128E Instruct FP8 | llama-4-maverick-17b-128e-instruct-fp8 | 128K | 8.2K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Grok 4 Fast (Non-Reasoning) | grok-4-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-09-19 |
| o3-mini | o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2024-05 | In: text Out: text | Released: 2024-12-20 Updated: 2025-01-29 |
| Embed v3 English | cohere-embed-v3-english | 512 | 1K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Open Weights Released: 2023-11-07 |
| Phi-3-medium-instruct (4k) | phi-3-medium-4k-instruct | 4.1K | 1K | Input: $0.17 Output: $0.68 | Model: 0.085 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Embed v3 Multilingual | cohere-embed-v3-multilingual | 512 | 1K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Open Weights Released: 2023-11-07 |
| GPT-3.5 Turbo 0125 | gpt-3.5-turbo-0125 | 16.4K | 16.4K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🌡️ | 2021-08 | In: text Out: text | Released: 2024-01-25 |
| Phi-4-mini-reasoning | phi-4-mini-reasoning | 128K | 4.1K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| Mistral Large 24.11 | mistral-large-2411 | 128K | 32.8K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | 2024-09 | In: text Out: text | Released: 2024-11-01 |
| GPT-5.1 Codex | gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image, audio Out: text, image, audio | Released: 2025-11-14 |
| Meta-Llama-3.1-8B-Instruct | meta-llama-3.1-8b-instruct | 128K | 32.8K | Input: $0.3 Output: $0.61 | Model: 0.150 Completion: 2.033 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| o1-preview | o1-preview | 128K | 32.8K | Input: $16.5 Output: $66 Cache Read: $8.25 | Model: 8.250 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2023-09 | In: text Out: text | Released: 2024-09-12 |
| Meta-Llama-3.1-70B-Instruct | meta-llama-3.1-70b-instruct | 128K | 32.8K | Input: $2.68 Output: $3.54 | Model: 1.340 Completion: 1.321 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Phi-3-mini-instruct (4k) | phi-3-mini-4k-instruct | 4.1K | 1K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Codex Mini | codex-mini | 200K | 100K | Input: $1.5 Output: $6 Cache Read: $0.375 | Model: 0.750 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-04 | In: text Out: text | Released: 2025-05-16 |
| Kimi K2 Thinking | kimi-k2-thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 Updated: 2025-12-02 |
| Phi-4-reasoning-plus | phi-4-reasoning-plus | 32K | 4.1K | Input: $0.125 Output: $0.5 | Model: 0.063 Completion: 4.000 | 🧠 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| GPT-4.1 mini | gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-05 | In: text, image Out: text | Released: 2025-04-14 |
| Phi-4 | phi-4 | 128K | 4.1K | Input: $0.125 Output: $0.5 | Model: 0.063 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| o4-mini | o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.28 | Model: 0.550 Completion: 4.000 Cache: 0.255 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-5 | gpt-5 | 272K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-4 32K | gpt-4-32k | 32.8K | 32.8K | Input: $60 Output: $120 | Model: 30.000 Completion: 2.000 | 🔧 🌡️ | 2023-11 | In: text Out: text | Released: 2023-03-14 |
| Grok 3 Mini | grok-3-mini | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 Reasoning: $0.5 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Embed v4 | cohere-embed-v-4-0 | 128K | 1.5K | Input: $0.12 Output: $0 | Model: 0.060 | 📎 | - | In: text, image Out: text | Open Weights Released: 2025-04-15 |
| DeepSeek-V3.2 | deepseek-v3.2 | 128K | 128K | Input: $0.58 Output: $1.68 | Model: 0.290 Completion: 2.897 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| Mistral Nemo | mistral-nemo | 128K | 128K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2024-07-18 |
| GPT-4 Turbo | gpt-4-turbo | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | 2023-11 | In: text, image Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| GPT-4.1 | gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-05 | In: text, image Out: text | Released: 2025-04-14 |
| Model Router | model-router | 128K | 16.4K | Input: $0.14 Output: $0 | Model: 0.070 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-05-19 Updated: 2025-11-18 |
| DeepSeek-V3-0324 | deepseek-v3-0324 | 131.1K | 131.1K | Input: $1.14 Output: $4.56 | Model: 0.570 Completion: 4.000 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-03-24 |
| Kimi K2.5 | kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 | Model: 0.300 Completion: 5.000 | 🧠 🔧 🌡️ | 2025-01 | In: text, image Out: text | Open Weights Released: 2026-02-06 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.125 | Model: 0.875 Completion: 8.000 Cache: 0.071 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-5.1 Codex Mini | gpt-5.1-codex-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-14 |
| text-embedding-3-large | text-embedding-3-large | 8.2K | 3.1K | Input: $0.13 Output: $0 | Model: 0.065 | - | - | In: text Out: text | Released: 2024-01-25 |
| GPT-3.5 Turbo 0613 | gpt-3.5-turbo-0613 | 16.4K | 16.4K | Input: $3 Output: $4 | Model: 1.500 Completion: 1.333 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-06-13 |
| Command R | cohere-command-r-08-2024 | 128K | 4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2024-08-30 |
| GPT-4.1 nano | gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 Cache Read: $0.03 | Model: 0.050 Completion: 4.000 Cache: 0.300 | 📎 🔧 🌡️ | 2024-05 | In: text, image Out: text | Released: 2025-04-14 |
| DeepSeek-V3.2-Speciale | deepseek-v3.2-speciale | 128K | 128K | Input: $0.58 Output: $1.68 | Model: 0.290 Completion: 2.897 | 🧠 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| Phi-4-mini | phi-4-mini | 128K | 4.1K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| DeepSeek-R1 | deepseek-r1 | 163.8K | 163.8K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-01-20 |
| text-embedding-3-small | text-embedding-3-small | 8.2K | 1.5K | Input: $0.02 Output: $0 | Model: 0.010 | - | - | In: text Out: text | Released: 2024-01-25 |
| GPT-3.5 Turbo 0301 | gpt-3.5-turbo-0301 | 4.1K | 4.1K | Input: $1.5 Output: $2 | Model: 0.750 Completion: 1.333 | 🌡️ | 2021-08 | In: text Out: text | Released: 2023-03-01 |
| DeepSeek-R1-0528 | deepseek-r1-0528 | 163.8K | 163.8K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-05-28 |
| Meta-Llama-3-70B-Instruct | meta-llama-3-70b-instruct | 8.2K | 2K | Input: $2.68 Output: $3.54 | Model: 1.340 Completion: 1.321 | 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-04-18 |
| Llama-3.2-11B-Vision-Instruct | llama-3.2-11b-vision-instruct | 128K | 8.2K | Input: $0.37 Output: $0.37 | Model: 0.185 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| o3 | o3 | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| Meta-Llama-3-8B-Instruct | meta-llama-3-8b-instruct | 8.2K | 2K | Input: $0.3 Output: $0.61 | Model: 0.150 Completion: 2.033 | 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-04-18 |
| GPT-5.1 Chat | gpt-5.1-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image, audio Out: text, image, audio | Released: 2025-11-14 |
| Grok 4 | grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 Reasoning: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-09 |
| GPT-5 Chat | gpt-5-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 | 2024-10-24 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-5.2 Chat | gpt-5.2-chat | 128K | 16.4K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| Command R+ | cohere-command-r-plus-08-2024 | 128K | 4K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2024-08-30 |
| Meta-Llama-3.1-405B-Instruct | meta-llama-3.1-405b-instruct | 128K | 32.8K | Input: $5.33 Output: $16 | Model: 2.665 Completion: 3.002 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama 4 Scout 17B 16E Instruct | llama-4-scout-17b-16e-instruct | 128K | 8.2K | Input: $0.2 Output: $0.78 | Model: 0.100 Completion: 3.900 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| GPT-5.1 | gpt-5.1 | 272K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image, audio Out: text, image, audio | Released: 2025-11-14 |
| o1 | o1 | 200K | 100K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2023-09 | In: text, image Out: text | Released: 2024-12-05 |
| DeepSeek-V3.1 | deepseek-v3.1 | 131.1K | 131.1K | Input: $0.56 Output: $1.68 | Model: 0.280 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-08-21 |
| Mistral Medium 3 | mistral-medium-2505 | 128K | 128K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-05-07 |
| Command A | cohere-command-a | 256K | 8K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2025-03-13 |
| Phi-3.5-mini-instruct | phi-3.5-mini-instruct | 128K | 4.1K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-08-20 |
| Llama-3.3-70B-Instruct | llama-3.3-70b-instruct | 128K | 32.8K | Input: $0.71 Output: $0.71 | Model: 0.355 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Grok Code Fast 1 | grok-code-fast-1 | 256K | 10K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Released: 2025-08-28 |
| Llama-3.2-90B-Vision-Instruct | llama-3.2-90b-vision-instruct | 128K | 8.2K | Input: $2.04 Output: $2.04 | Model: 1.020 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Grok 3 | grok-3 | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| GPT-5.2 Codex | gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2026-01-14 |
| Ministral 3B | ministral-3b | 128K | 8.2K | Input: $0.04 Output: $0.04 | Model: 0.020 Completion: 1.000 | 🔧 🌡️ | 2024-03 | In: text Out: text | Open Weights Released: 2024-10-22 |
| GPT-4 Turbo Vision | gpt-4-turbo-vision | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | 2023-11 | In: text, image Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| Phi-3.5-MoE-instruct | phi-3.5-moe-instruct | 128K | 4.1K | Input: $0.16 Output: $0.64 | Model: 0.080 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-08-20 |
| MAI-DS-R1 | mai-ds-r1 | 128K | 8.2K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🌡️ | 2024-06 | In: text Out: text | Released: 2025-01-20 |
| Phi-4-multimodal | phi-4-multimodal | 128K | 4.1K | Input: $0.08 Output: $0.32 Input Audio: $4 | Model: 2.000 Completion: 0.080 | 📎 🌡️ | 2023-10 | In: text, image, audio Out: text | Open Weights Released: 2024-12-11 |
| Phi-3-medium-instruct (128k) | phi-3-medium-128k-instruct | 128K | 4.1K | Input: $0.17 Output: $0.68 | Model: 0.085 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Grok 4 Fast (Reasoning) | grok-4-fast-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-09-19 |
| text-embedding-ada-002 | text-embedding-ada-002 | 8.2K | 1.5K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Released: 2022-12-15 |
| GPT-4o mini | gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.08 | Model: 0.075 Completion: 4.000 Cache: 0.533 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-07-18 |
| Phi-3-small-instruct (128k) | phi-3-small-128k-instruct | 128K | 4.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| GPT-5 Pro | gpt-5-pro | 400K | 272K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-10-06 |
| GPT-5-Codex | gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
Bailing¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Ring-1T | Ring-1T | 128K | 32K | Input: $0.57 Output: $2.29 | Model: 0.285 Completion: 4.018 | 🧠 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-10 |
| Ling-1T | Ling-1T | 128K | 32K | Input: $0.57 Output: $2.29 | Model: 0.285 Completion: 4.018 | 🔧 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-10 |
Baseten¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 4.6 | zai-org/GLM-4.6 | 200K | 200K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🔧 🌡️ | 2025-08-31 | In: text Out: text | Open Weights Released: 2025-09-16 |
| GLM-4.7 | zai-org/GLM-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-5 | zai-org/GLM-5 | 202.8K | 131.1K | Input: $0.95 Output: $3.15 | Model: 0.475 Completion: 3.316 | 🧠 🔧 🌡️ | 2026-01 | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax-M2.5 | MiniMaxAI/MiniMax-M2.5 | 204K | 204K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | 2026-01 | In: text Out: text | Open Weights Released: 2026-02-12 |
| DeepSeek V3.2 | deepseek-ai/DeepSeek-V3.2 | 163.8K | 131.1K | Input: $0.3 Output: $0.45 | Model: 0.150 Completion: 1.500 | 🔧 🌡️ | 2025-10 | In: text Out: text | Open Weights Released: 2025-12-01 |
| Kimi K2 Instruct 0905 | moonshotai/Kimi-K2-Instruct-0905 | 262.1K | 262.1K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🔧 🌡️ | 2025-08 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2.5 | moonshotai/Kimi-K2.5 | 262.1K | 8.2K | Input: $0.6 Output: $3 | Model: 0.300 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-30 Updated: 2026-02-12 |
| Kimi K2 Thinking | moonshotai/Kimi-K2-Thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Qwen3 Coder 480B A35B Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct | 262.1K | 66.5K | Input: $0.38 Output: $1.53 | Model: 0.190 Completion: 4.026 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
Berget.AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 4.7 | zai-org/GLM-4.7 | 128K | 8.2K | Input: $0.7 Output: $2.3 | Model: 0.350 Completion: 3.286 | 🧠 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-19 |
| bge-reranker-v2-m3 | BAAI/bge-reranker-v2-m3 | 512 | 512 | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | - | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-23 |
| Multilingual-E5-large-instruct | intfloat/multilingual-e5-large-instruct | 512 | 1K | Input: $0.02 Output: $0 | Model: 0.010 | - | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-27 |
| Multilingual-E5-large | intfloat/multilingual-e5-large | 512 | 1K | Input: $0.02 Output: $0 | Model: 0.010 | - | 2025-09 | In: text Out: text | Open Weights Released: 2025-09-11 |
| KB-Whisper-Large | KBLab/kb-whisper-large | 480K | 4.8K | Input: $3 Output: $3 | Model: 1.500 Completion: 1.000 | - | 2025-04 | In: audio Out: text | Open Weights Released: 2025-04-27 |
| Llama 3.3 70B Instruct | meta-llama/Llama-3.3-70B-Instruct | 128K | 8.2K | Input: $0.9 Output: $0.9 | Model: 0.450 Completion: 1.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-04-27 |
| Mistral Small 3.2 24B Instruct 2506 | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | 32K | 8.2K | Input: $0.3 Output: $0.3 | Model: 0.150 Completion: 1.000 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2025-10-01 |
| GPT-OSS-120B | openai/gpt-oss-120b | 128K | 8.2K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-08 | In: text Out: text | Open Weights Released: 2025-08-05 |
Cerebras¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Qwen 3 235B Instruct | qwen-3-235b-a22b-instruct-2507 | 131K | 32K | Input: $0.6 Output: $1.2 | Model: 0.300 Completion: 2.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-22 |
| GPT OSS 120B | gpt-oss-120b | 131.1K | 32.8K | Input: $0.25 Output: $0.69 | Model: 0.125 Completion: 2.760 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| Llama 3.1 8B | llama3.1-8b | 32K | 8K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Z.AI GLM-4.7 | zai-glm-4.7 | 131.1K | 40K | Input: $2.25 Output: $2.75 Cache Read: $0 Cache Write: $0 | Model: 1.125 Completion: 1.222 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-10 |
Chutes¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 4.7 FP8 | zai-org/GLM-4.7-FP8 | 202.8K | 65.5K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-27 |
| GLM 4.5 Air | zai-org/GLM-4.5-Air | 131.1K | 131.1K | Input: $0.05 Output: $0.22 | Model: 0.025 Completion: 4.400 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| GLM 4.7 Flash | zai-org/GLM-4.7-Flash | 202.8K | 65.5K | Input: $0.06 Output: $0.35 | Model: 0.030 Completion: 5.833 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-27 |
| GLM 4.7 TEE | zai-org/GLM-4.7-TEE | 202.8K | 65.5K | Input: $0.4 Output: $1.5 | Model: 0.200 Completion: 3.750 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| GLM 4.6 TEE | zai-org/GLM-4.6-TEE | 202.8K | 65.5K | Input: $0.35 Output: $1.5 | Model: 0.175 Completion: 4.286 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| GLM 4.5 FP8 | zai-org/GLM-4.5-FP8 | 131.1K | 65.5K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-27 |
| GLM 5 TEE | zai-org/GLM-5-TEE | 202.8K | 65.5K | Input: $0.75 Output: $2.5 | Model: 0.375 Completion: 3.333 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-14 |
| GLM 4.6V | zai-org/GLM-4.6V | 131.1K | 65.5K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| GLM 4.6 FP8 | zai-org/GLM-4.6-FP8 | 202.8K | 65.5K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-27 |
| GLM 4.5 TEE | zai-org/GLM-4.5-TEE | 131.1K | 65.5K | Input: $0.35 Output: $1.55 | Model: 0.175 Completion: 4.429 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| NVIDIA Nemotron 3 Nano 30B A3B BF16 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 262.1K | 262.1K | Input: $0.06 Output: $0.24 | Model: 0.030 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Hermes 4.3 36B | NousResearch/Hermes-4.3-36B | 32.8K | 8.2K | Input: $0.1 Output: $0.39 | Model: 0.050 Completion: 3.900 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepHermes 3 Mistral 24B Preview | NousResearch/DeepHermes-3-Mistral-24B-Preview | 32.8K | 32.8K | Input: $0.02 Output: $0.1 | Model: 0.010 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Hermes 4 14B | NousResearch/Hermes-4-14B | 41K | 41K | Input: $0.01 Output: $0.05 | Model: 0.005 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Hermes 4 405B FP8 TEE | NousResearch/Hermes-4-405B-FP8-TEE | 131.1K | 65.5K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Hermes 4 70B | NousResearch/Hermes-4-70B | 131.1K | 131.1K | Input: $0.11 Output: $0.38 | Model: 0.055 Completion: 3.455 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| MiMo V2 Flash | XiaomiMiMo/MiMo-V2-Flash | 32.8K | 8.2K | Input: $0.09 Output: $0.29 | Model: 0.045 Completion: 3.222 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-27 |
| MiniMax M2.5 TEE | MiniMaxAI/MiniMax-M2.5-TEE | 196.6K | 65.5K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-15 |
| MiniMax M2.1 TEE | MiniMaxAI/MiniMax-M2.1-TEE | 196.6K | 65.5K | Input: $0.27 Output: $1.12 | Model: 0.135 Completion: 4.148 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-27 |
| DeepSeek V3.1 Terminus TEE | deepseek-ai/DeepSeek-V3.1-Terminus-TEE | 163.8K | 65.5K | Input: $0.23 Output: $0.9 | Model: 0.115 Completion: 3.913 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek V3.2 TEE | deepseek-ai/DeepSeek-V3.2-TEE | 163.8K | 65.5K | Input: $0.25 Output: $0.38 Cache Read: $0.125 | Model: 0.125 Completion: 1.520 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek V3 0324 TEE | deepseek-ai/DeepSeek-V3-0324-TEE | 163.8K | 65.5K | Input: $0.19 Output: $0.87 Cache Read: $0.095 | Model: 0.095 Completion: 4.579 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek V3.2 Speciale TEE | deepseek-ai/DeepSeek-V3.2-Speciale-TEE | 163.8K | 65.5K | Input: $0.27 Output: $0.41 | Model: 0.135 Completion: 1.519 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek R1 TEE | deepseek-ai/DeepSeek-R1-TEE | 163.8K | 163.8K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek V3 | deepseek-ai/DeepSeek-V3 | 163.8K | 163.8K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek R1 Distill Llama 70B | deepseek-ai/DeepSeek-R1-Distill-Llama-70B | 131.1K | 131.1K | Input: $0.03 Output: $0.11 | Model: 0.015 Completion: 3.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek V3.1 TEE | deepseek-ai/DeepSeek-V3.1-TEE | 163.8K | 65.5K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek R1 0528 TEE | deepseek-ai/DeepSeek-R1-0528-TEE | 163.8K | 65.5K | Input: $0.4 Output: $1.75 | Model: 0.200 Completion: 4.375 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| dots.ocr | rednote-hilab/dots.ocr | 131.1K | 131.1K | Input: $0.01 Output: $0.01 Cache Read: $0.005 | Model: 0.005 Completion: 1.000 Cache: 0.500 | 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Mistral Nemo Instruct 2407 | unsloth/Mistral-Nemo-Instruct-2407 | 131.1K | 131.1K | Input: $0.02 Output: $0.04 Cache Read: $0.01 | Model: 0.010 Completion: 2.000 Cache: 0.500 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Mistral Small 24B Instruct 2501 | unsloth/Mistral-Small-24B-Instruct-2501 | 32.8K | 32.8K | Input: $0.03 Output: $0.11 | Model: 0.015 Completion: 3.667 | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| gemma 3 12b it | unsloth/gemma-3-12b-it | 131.1K | 131.1K | Input: $0.03 Output: $0.1 | Model: 0.015 Completion: 3.333 | 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| gemma 3 4b it | unsloth/gemma-3-4b-it | 96K | 96K | Input: $0.01 Output: $0.03 | Model: 0.005 Completion: 3.000 | 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| gemma 3 27b it | unsloth/gemma-3-27b-it | 128K | 65.5K | Input: $0.04 Output: $0.15 Cache Read: $0.02 | Model: 0.020 Completion: 3.750 Cache: 0.500 | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Llama 3.2 1B Instruct | unsloth/Llama-3.2-1B-Instruct | 32.8K | 8.2K | Input: $0.01 Output: $0.01 Cache Read: $0.005 | Model: 0.005 Completion: 1.000 Cache: 0.500 | 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-27 |
| Llama 3.2 3B Instruct | unsloth/Llama-3.2-3B-Instruct | 16.4K | 16.4K | Input: $0.01 Output: $0.01 Cache Read: $0.005 | Model: 0.005 Completion: 1.000 Cache: 0.500 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-02-12 |
| Kimi K2 Instruct 0905 | moonshotai/Kimi-K2-Instruct-0905 | 262.1K | 262.1K | Input: $0.39 Output: $1.9 Cache Read: $0.195 | Model: 0.195 Completion: 4.872 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Kimi K2.5 TEE | moonshotai/Kimi-K2.5-TEE | 262.1K | 65.5K | Input: $0.6 Output: $3 | Model: 0.300 Completion: 5.000 | 🧠 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking TEE | moonshotai/Kimi-K2-Thinking-TEE | 262.1K | 65.5K | Input: $0.4 Output: $1.75 | Model: 0.200 Completion: 4.375 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 30B A3B | Qwen/Qwen3-30B-A3B | 41K | 41K | Input: $0.06 Output: $0.22 | Model: 0.030 Completion: 3.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 30B A3B Instruct 2507 | Qwen/Qwen3-30B-A3B-Instruct-2507 | 262.1K | 262.1K | Input: $0.08 Output: $0.33 | Model: 0.040 Completion: 4.125 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 VL 235B A22B Instruct | Qwen/Qwen3-VL-235B-A22B-Instruct | 262.1K | 262.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3.5 397B A17B TEE | Qwen/Qwen3.5-397B-A17B-TEE | 262.1K | 65.5K | Input: $0.3 Output: $1.2 Cache Read: $0.15 | Model: 0.150 Completion: 4.000 Cache: 0.500 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-02-18 |
| Qwen3 32B | Qwen/Qwen3-32B | 41K | 41K | Input: $0.08 Output: $0.24 Cache Read: $0.04 | Model: 0.040 Completion: 3.000 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 Next 80B A3B Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | 262.1K | 262.1K | Input: $0.1 Output: $0.8 | Model: 0.050 Completion: 8.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 235B A22B Thinking 2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262.1K | 262.1K | Input: $0.11 Output: $0.6 | Model: 0.055 Completion: 5.455 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 Coder Next | Qwen/Qwen3-Coder-Next | 262.1K | 65.5K | Input: $0.07 Output: $0.3 | Model: 0.035 Completion: 4.286 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-05 |
| Qwen2.5 Coder 32B Instruct | Qwen/Qwen2.5-Coder-32B-Instruct | 32.8K | 32.8K | Input: $0.03 Output: $0.11 | Model: 0.015 Completion: 3.667 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 Coder 480B A35B Instruct FP8 TEE | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE | 262.1K | 262.1K | Input: $0.22 Output: $0.95 Cache Read: $0.11 | Model: 0.110 Completion: 4.318 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen2.5 72B Instruct | Qwen/Qwen2.5-72B-Instruct | 32.8K | 32.8K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 235B A22B Instruct 2507 TEE | Qwen/Qwen3-235B-A22B-Instruct-2507-TEE | 262.1K | 65.5K | Input: $0.08 Output: $0.55 Cache Read: $0.04 | Model: 0.040 Completion: 6.875 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 235B A22B | Qwen/Qwen3-235B-A22B | 41K | 41K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen2.5 VL 72B Instruct TEE | Qwen/Qwen2.5-VL-72B-Instruct-TEE | 32.8K | 32.8K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3Guard Gen 0.6B | Qwen/Qwen3Guard-Gen-0.6B | 32.8K | 8.2K | Input: $0.01 Output: $0.01 Cache Read: $0.005 | Model: 0.005 Completion: 1.000 Cache: 0.500 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen3 14B | Qwen/Qwen3-14B | 41K | 41K | Input: $0.05 Output: $0.22 | Model: 0.025 Completion: 4.400 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Qwen2.5 VL 32B Instruct | Qwen/Qwen2.5-VL-32B-Instruct | 16.4K | 16.4K | Input: $0.05 Output: $0.22 | Model: 0.025 Completion: 4.400 | 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek R1T Chimera | tngtech/DeepSeek-R1T-Chimera | 163.8K | 163.8K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| DeepSeek TNG R1T2 Chimera | tngtech/DeepSeek-TNG-R1T2-Chimera | 163.8K | 163.8K | Input: $0.25 Output: $0.85 | Model: 0.125 Completion: 3.400 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| TNG R1T Chimera Turbo | tngtech/TNG-R1T-Chimera-Turbo | 163.8K | 65.5K | Input: $0.22 Output: $0.6 | Model: 0.110 Completion: 2.727 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-27 |
| TNG R1T Chimera TEE | tngtech/TNG-R1T-Chimera-TEE | 163.8K | 65.5K | Input: $0.25 Output: $0.85 | Model: 0.125 Completion: 3.400 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Devstral 2 123B Instruct 2512 TEE | mistralai/Devstral-2-123B-Instruct-2512-TEE | 262.1K | 65.5K | Input: $0.05 Output: $0.22 | Model: 0.025 Completion: 4.400 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-10 |
| gpt oss 120b TEE | openai/gpt-oss-120b-TEE | 131.1K | 65.5K | Input: $0.04 Output: $0.18 | Model: 0.020 Completion: 4.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| gpt oss 20b | openai/gpt-oss-20b | 131.1K | 131.1K | Input: $0.02 Output: $0.1 | Model: 0.010 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Mistral Small 3.2 24B Instruct 2506 | chutesai/Mistral-Small-3.2-24B-Instruct-2506 | 131.1K | 131.1K | Input: $0.06 Output: $0.18 | Model: 0.030 Completion: 3.000 | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Mistral Small 3.1 24B Instruct 2503 | chutesai/Mistral-Small-3.1-24B-Instruct-2503 | 131.1K | 131.1K | Input: $0.03 Output: $0.11 Cache Read: $0.015 | Model: 0.015 Completion: 3.667 Cache: 0.500 | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| MiroThinker V1.5 235B | miromind-ai/MiroThinker-v1.5-235B | 262.1K | 8.2K | Input: $0.3 Output: $1.2 Cache Read: $0.15 | Model: 0.150 Completion: 4.000 Cache: 0.500 | 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-10 |
| InternVL3 78B TEE | OpenGVLab/InternVL3-78B-TEE | 32.8K | 32.8K | Input: $0.1 Output: $0.39 | Model: 0.050 Completion: 3.900 | 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-01-06 Updated: 2026-01-10 |
CloudFerro Sherlock¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Bielik 11B v2.6 Instruct | speakleash/Bielik-11B-v2.6-Instruct | 32K | 32K | Input: $0.67 Output: $0.67 | Model: 0.335 Completion: 1.000 | 🔧 🌡️ | 2025-03 | In: text Out: text | Open Weights Released: 2025-03-13 |
| Bielik 11B v3.0 Instruct | speakleash/Bielik-11B-v3.0-Instruct | 32K | 32K | Input: $0.67 Output: $0.67 | Model: 0.335 Completion: 1.000 | 🔧 🌡️ | 2025-03 | In: text Out: text | Open Weights Released: 2025-03-13 |
| Llama 3.3 70B Instruct | meta-llama/Llama-3.3-70B-Instruct | 70K | 70K | Input: $2.92 Output: $2.92 | Model: 1.460 Completion: 1.000 | 🔧 🌡️ | 2024-10-09 | In: text Out: text | Open Weights Released: 2024-12-06 |
| OpenAI GPT OSS 120B | openai/gpt-oss-120b | 131K | 131K | Input: $2.92 Output: $2.92 | Model: 1.460 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-28 |
Cloudflare AI Gateway¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| IBM Granite 4.0 H Micro | workers-ai/cf/ibm-granite/granite-4.0-h-micro | 128K | 16.4K | Input: $0.017 Output: $0.11 | Model: 0.009 Completion: 6.471 | 🌡️ | - | In: text Out: text | Released: 2025-10-15 |
| BGE Small EN v1.5 | workers-ai/cf/baai/bge-small-en-v1.5 | 128K | 16.4K | Input: $0.02 Output: $0 | Model: 0.010 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BGE Large EN v1.5 | workers-ai/cf/baai/bge-large-en-v1.5 | 128K | 16.4K | Input: $0.2 Output: $0 | Model: 0.100 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BGE Reranker Base | workers-ai/cf/baai/bge-reranker-base | 128K | 16.4K | Input: $0.0031 Output: $0 | Model: 0.002 | 🌡️ | - | In: text Out: text | Released: 2025-04-09 |
| BGE M3 | workers-ai/cf/baai/bge-m3 | 128K | 16.4K | Input: $0.012 Output: $0 | Model: 0.006 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BGE Base EN v1.5 | workers-ai/cf/baai/bge-base-en-v1.5 | 128K | 16.4K | Input: $0.067 Output: $0 | Model: 0.034 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| PLaMo Embedding 1B | workers-ai/cf/pfnet/plamo-embedding-1b | 128K | 16.4K | Input: $0.019 Output: $0 | Model: 0.009 | 🌡️ | - | In: text Out: text | Released: 2025-09-25 |
| DeepSeek R1 Distill Qwen 32B | workers-ai/cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 128K | 16.4K | Input: $0.5 Output: $4.88 | Model: 0.250 Completion: 9.760 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BART Large CNN | workers-ai/cf/facebook/bart-large-cnn | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-04-09 |
| Mistral 7B Instruct v0.1 | workers-ai/cf/mistral/mistral-7b-instruct-v0.1 | 128K | 16.4K | Input: $0.11 Output: $0.19 | Model: 0.055 Completion: 1.727 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| MyShell MeloTTS | workers-ai/cf/myshell-ai/melotts | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Pipecat Smart Turn v2 | workers-ai/cf/pipecat-ai/smart-turn-v2 | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Gemma 3 12B IT | workers-ai/cf/google/gemma-3-12b-it | 128K | 16.4K | Input: $0.35 Output: $0.56 | Model: 0.175 Completion: 1.600 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| QwQ 32B | workers-ai/cf/qwen/qwq-32b | 128K | 16.4K | Input: $0.66 Output: $1 | Model: 0.330 Completion: 1.515 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| Qwen3 30B A3B FP8 | workers-ai/cf/qwen/qwen3-30b-a3b-fp8 | 128K | 16.4K | Input: $0.051 Output: $0.34 | Model: 0.025 Completion: 6.667 | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Qwen 2.5 Coder 32B Instruct | workers-ai/cf/qwen/qwen2.5-coder-32b-instruct | 128K | 16.4K | Input: $0.66 Output: $1 | Model: 0.330 Completion: 1.515 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| Qwen3 Embedding 0.6B | workers-ai/cf/qwen/qwen3-embedding-0.6b | 128K | 16.4K | Input: $0.012 Output: $0 | Model: 0.006 | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Llama 3.1 8B Instruct FP8 | workers-ai/cf/meta/llama-3.1-8b-instruct-fp8 | 128K | 16.4K | Input: $0.15 Output: $0.29 | Model: 0.075 Completion: 1.933 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3 8B Instruct AWQ | workers-ai/cf/meta/llama-3-8b-instruct-awq | 128K | 16.4K | Input: $0.12 Output: $0.27 | Model: 0.060 Completion: 2.250 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.1 8B Instruct AWQ | workers-ai/cf/meta/llama-3.1-8b-instruct-awq | 128K | 16.4K | Input: $0.12 Output: $0.27 | Model: 0.060 Completion: 2.250 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 4 Scout 17B 16E Instruct | workers-ai/cf/meta/llama-4-scout-17b-16e-instruct | 128K | 16.4K | Input: $0.27 Output: $0.85 | Model: 0.135 Completion: 3.148 | 🌡️ | - | In: text Out: text | Released: 2025-04-16 |
| Llama 3.2 11B Vision Instruct | workers-ai/cf/meta/llama-3.2-11b-vision-instruct | 128K | 16.4K | Input: $0.049 Output: $0.68 | Model: 0.025 Completion: 13.878 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.2 3B Instruct | workers-ai/cf/meta/llama-3.2-3b-instruct | 128K | 16.4K | Input: $0.051 Output: $0.34 | Model: 0.025 Completion: 6.667 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama Guard 3 8B | workers-ai/cf/meta/llama-guard-3-8b | 128K | 16.4K | Input: $0.48 Output: $0.03 | Model: 0.240 Completion: 0.063 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.2 1B Instruct | workers-ai/cf/meta/llama-3.2-1b-instruct | 128K | 16.4K | Input: $0.027 Output: $0.2 | Model: 0.013 Completion: 7.407 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.3 70B Instruct FP8 Fast | workers-ai/cf/meta/llama-3.3-70b-instruct-fp8-fast | 128K | 16.4K | Input: $0.29 Output: $2.25 | Model: 0.145 Completion: 7.759 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.1 8B Instruct | workers-ai/cf/meta/llama-3.1-8b-instruct | 128K | 16.4K | Input: $0.28 Output: $0.8299999999999998 | Model: 0.140 Completion: 2.964 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| M2M100 1.2B | workers-ai/cf/meta/m2m100-1.2b | 128K | 16.4K | Input: $0.34 Output: $0.34 | Model: 0.170 Completion: 1.000 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 2 7B Chat FP16 | workers-ai/cf/meta/llama-2-7b-chat-fp16 | 128K | 16.4K | Input: $0.56 Output: $6.67 | Model: 0.280 Completion: 11.911 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3 8B Instruct | workers-ai/cf/meta/llama-3-8b-instruct | 128K | 16.4K | Input: $0.28 Output: $0.83 | Model: 0.140 Completion: 2.964 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Mistral Small 3.1 24B Instruct | workers-ai/cf/mistralai/mistral-small-3.1-24b-instruct | 128K | 16.4K | Input: $0.35 Output: $0.56 | Model: 0.175 Completion: 1.600 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| Deepgram Aura 2 (ES) | workers-ai/cf/deepgram/aura-2-es | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Deepgram Nova 3 | workers-ai/cf/deepgram/nova-3 | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Deepgram Aura 2 (EN) | workers-ai/cf/deepgram/aura-2-en | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| GPT OSS 120B | workers-ai/cf/openai/gpt-oss-120b | 128K | 16.4K | Input: $0.35 Output: $0.75 | Model: 0.175 Completion: 2.143 | 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| GPT OSS 20B | workers-ai/cf/openai/gpt-oss-20b | 128K | 16.4K | Input: $0.2 Output: $0.3 | Model: 0.100 Completion: 1.500 | 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| IndicTrans2 EN-Indic 1B | workers-ai/cf/ai4bharat/indictrans2-en-indic-1B | 128K | 16.4K | Input: $0.34 Output: $0.34 | Model: 0.170 Completion: 1.000 | 🌡️ | - | In: text Out: text | Released: 2025-09-25 |
| DistilBERT SST-2 INT8 | workers-ai/cf/huggingface/distilbert-sst-2-int8 | 128K | 16.4K | Input: $0.026 Output: $0 | Model: 0.013 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Gemma SEA-LION v4 27B IT | workers-ai/cf/aisingapore/gemma-sea-lion-v4-27b-it | 128K | 16.4K | Input: $0.35 Output: $0.56 | Model: 0.175 Completion: 1.600 | 🌡️ | - | In: text Out: text | Released: 2025-09-25 |
| GPT-4o mini | openai/gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.08 | Model: 0.075 Completion: 4.000 Cache: 0.533 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-07-18 |
| o1 | openai/o1 | 200K | 100K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | 📎 🧠 🔧 | 2023-09 | In: text, image Out: text | Released: 2024-12-05 |
| GPT-5.1 | openai/gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| o3 | openai/o3 | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-3.5-turbo | openai/gpt-3.5-turbo | 16.4K | 4.1K | Input: $0.5 Output: $1.5 Cache Read: $1.25 | Model: 0.250 Completion: 3.000 Cache: 2.500 | 🌡️ | 2021-09-01 | In: text Out: text | Released: 2023-03-01 Updated: 2023-11-06 |
| GPT-5.2 | openai/gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| o3-pro | openai/o3-pro | 200K | 100K | Input: $20 Output: $80 | Model: 10.000 Completion: 4.000 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-06-10 |
| GPT-4 Turbo | openai/gpt-4-turbo | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| o4-mini | openai/o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.28 | Model: 0.550 Completion: 4.000 Cache: 0.255 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-5.1 Codex | openai/gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| o3-mini | openai/o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2024-05 | In: text Out: text | Released: 2024-12-20 Updated: 2025-01-29 |
| GPT-4 | openai/gpt-4 | 8.2K | 8.2K | Input: $30 Output: $60 | Model: 15.000 Completion: 2.000 | 📎 🔧 🌡️ | 2023-11 | In: text Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| GPT-4o | openai/gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 Updated: 2024-08-06 |
| Claude Sonnet 3.5 v2 | anthropic/claude-3.5-sonnet | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04-30 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Opus 4.1 (latest) | anthropic/claude-opus-4-1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude Sonnet 3 | anthropic/claude-3-sonnet | 200K | 4.1K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $0.3 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-03-04 |
| Claude Haiku 3.5 (latest) | anthropic/claude-3-5-haiku | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Opus 4.6 (latest) | anthropic/claude-opus-4-6 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Claude Haiku 3 | anthropic/claude-3-haiku | 200K | 4.1K | Input: $0.25 Output: $1.25 Cache Read: $0.03 Cache Write: $0.3 | Model: 0.125 Completion: 5.000 Cache: 0.120 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-03-13 |
| Claude Sonnet 4.6 | anthropic/claude-sonnet-4-6 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Claude Haiku 3.5 (latest) | anthropic/claude-3.5-haiku | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Opus 4 (latest) | anthropic/claude-opus-4 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Haiku 4.5 (latest) | anthropic/claude-haiku-4-5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Opus 4.5 (latest) | anthropic/claude-opus-4-5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Claude Opus 3 | anthropic/claude-3-opus | 200K | 4.1K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-02-29 |
| Claude Sonnet 4 (latest) | anthropic/claude-sonnet-4 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 4.5 (latest) | anthropic/claude-sonnet-4-5 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
Cloudflare Workers AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| IBM Granite 4.0 H Micro | cf/ibm-granite/granite-4.0-h-micro | 128K | 16.4K | Input: $0.017 Output: $0.11 | Model: 0.009 Completion: 6.471 | 🌡️ | - | In: text Out: text | Released: 2025-10-15 |
| BGE Small EN v1.5 | cf/baai/bge-small-en-v1.5 | 128K | 16.4K | Input: $0.02 Output: $0 | Model: 0.010 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BGE Large EN v1.5 | cf/baai/bge-large-en-v1.5 | 128K | 16.4K | Input: $0.2 Output: $0 | Model: 0.100 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BGE Reranker Base | cf/baai/bge-reranker-base | 128K | 16.4K | Input: $0.0031 Output: $0 | Model: 0.002 | 🌡️ | - | In: text Out: text | Released: 2025-04-09 |
| BGE M3 | cf/baai/bge-m3 | 128K | 16.4K | Input: $0.012 Output: $0 | Model: 0.006 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BGE Base EN v1.5 | cf/baai/bge-base-en-v1.5 | 128K | 16.4K | Input: $0.067 Output: $0 | Model: 0.034 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| PLaMo Embedding 1B | cf/pfnet/plamo-embedding-1b | 128K | 16.4K | Input: $0.019 Output: $0 | Model: 0.009 | 🌡️ | - | In: text Out: text | Released: 2025-09-25 |
| DeepSeek R1 Distill Qwen 32B | cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 128K | 16.4K | Input: $0.5 Output: $4.88 | Model: 0.250 Completion: 9.760 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| BART Large CNN | cf/facebook/bart-large-cnn | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-04-09 |
| Mistral 7B Instruct v0.1 | cf/mistral/mistral-7b-instruct-v0.1 | 128K | 16.4K | Input: $0.11 Output: $0.19 | Model: 0.055 Completion: 1.727 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| MyShell MeloTTS | cf/myshell-ai/melotts | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Pipecat Smart Turn v2 | cf/pipecat-ai/smart-turn-v2 | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Gemma 3 12B IT | cf/google/gemma-3-12b-it | 128K | 16.4K | Input: $0.35 Output: $0.56 | Model: 0.175 Completion: 1.600 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| QwQ 32B | cf/qwen/qwq-32b | 128K | 16.4K | Input: $0.66 Output: $1 | Model: 0.330 Completion: 1.515 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| Qwen3 30B A3B FP8 | cf/qwen/qwen3-30b-a3b-fp8 | 128K | 16.4K | Input: $0.051 Output: $0.34 | Model: 0.025 Completion: 6.667 | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Qwen 2.5 Coder 32B Instruct | cf/qwen/qwen2.5-coder-32b-instruct | 128K | 16.4K | Input: $0.66 Output: $1 | Model: 0.330 Completion: 1.515 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| Qwen3 Embedding 0.6B | cf/qwen/qwen3-embedding-0.6b | 128K | 16.4K | Input: $0.012 Output: $0 | Model: 0.006 | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Llama 3.1 8B Instruct FP8 | cf/meta/llama-3.1-8b-instruct-fp8 | 128K | 16.4K | Input: $0.15 Output: $0.29 | Model: 0.075 Completion: 1.933 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3 8B Instruct AWQ | cf/meta/llama-3-8b-instruct-awq | 128K | 16.4K | Input: $0.12 Output: $0.27 | Model: 0.060 Completion: 2.250 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.1 8B Instruct AWQ | cf/meta/llama-3.1-8b-instruct-awq | 128K | 16.4K | Input: $0.12 Output: $0.27 | Model: 0.060 Completion: 2.250 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 4 Scout 17B 16E Instruct | cf/meta/llama-4-scout-17b-16e-instruct | 128K | 16.4K | Input: $0.27 Output: $0.85 | Model: 0.135 Completion: 3.148 | 🌡️ | - | In: text Out: text | Released: 2025-04-16 |
| Llama 3.2 11B Vision Instruct | cf/meta/llama-3.2-11b-vision-instruct | 128K | 16.4K | Input: $0.049 Output: $0.68 | Model: 0.025 Completion: 13.878 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.2 3B Instruct | cf/meta/llama-3.2-3b-instruct | 128K | 16.4K | Input: $0.051 Output: $0.34 | Model: 0.025 Completion: 6.667 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama Guard 3 8B | cf/meta/llama-guard-3-8b | 128K | 16.4K | Input: $0.48 Output: $0.03 | Model: 0.240 Completion: 0.063 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.2 1B Instruct | cf/meta/llama-3.2-1b-instruct | 128K | 16.4K | Input: $0.027 Output: $0.2 | Model: 0.013 Completion: 7.407 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.3 70B Instruct FP8 Fast | cf/meta/llama-3.3-70b-instruct-fp8-fast | 128K | 16.4K | Input: $0.29 Output: $2.25 | Model: 0.145 Completion: 7.759 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3.1 8B Instruct | cf/meta/llama-3.1-8b-instruct | 128K | 16.4K | Input: $0.28 Output: $0.8299999999999998 | Model: 0.140 Completion: 2.964 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| M2M100 1.2B | cf/meta/m2m100-1.2b | 128K | 16.4K | Input: $0.34 Output: $0.34 | Model: 0.170 Completion: 1.000 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 2 7B Chat FP16 | cf/meta/llama-2-7b-chat-fp16 | 128K | 16.4K | Input: $0.56 Output: $6.67 | Model: 0.280 Completion: 11.911 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Llama 3 8B Instruct | cf/meta/llama-3-8b-instruct | 128K | 16.4K | Input: $0.28 Output: $0.83 | Model: 0.140 Completion: 2.964 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Mistral Small 3.1 24B Instruct | cf/mistralai/mistral-small-3.1-24b-instruct | 128K | 16.4K | Input: $0.35 Output: $0.56 | Model: 0.175 Completion: 1.600 | 🌡️ | - | In: text Out: text | Released: 2025-04-11 |
| Deepgram Aura 2 (ES) | cf/deepgram/aura-2-es | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Deepgram Nova 3 | cf/deepgram/nova-3 | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| Deepgram Aura 2 (EN) | cf/deepgram/aura-2-en | 128K | 16.4K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-11-14 |
| GPT OSS 120B | cf/openai/gpt-oss-120b | 128K | 16.4K | Input: $0.35 Output: $0.75 | Model: 0.175 Completion: 2.143 | 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| GPT OSS 20B | cf/openai/gpt-oss-20b | 128K | 16.4K | Input: $0.2 Output: $0.3 | Model: 0.100 Completion: 1.500 | 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| IndicTrans2 EN-Indic 1B | cf/ai4bharat/indictrans2-en-indic-1B | 128K | 16.4K | Input: $0.34 Output: $0.34 | Model: 0.170 Completion: 1.000 | 🌡️ | - | In: text Out: text | Released: 2025-09-25 |
| DistilBERT SST-2 INT8 | cf/huggingface/distilbert-sst-2-int8 | 128K | 16.4K | Input: $0.026 Output: $0 | Model: 0.013 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Gemma SEA-LION v4 27B IT | cf/aisingapore/gemma-sea-lion-v4-27b-it | 128K | 16.4K | Input: $0.35 Output: $0.56 | Model: 0.175 Completion: 1.600 | 🌡️ | - | In: text Out: text | Released: 2025-09-25 |
Cohere¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Aya Expanse 32B | c4ai-aya-expanse-32b | 128K | 4K | - | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-10-24 |
| Command A | command-a-03-2025 | 256K | 8K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2025-03-13 |
| Command R7B Arabic | command-r7b-arabic-02-2025 | 128K | 4K | Input: $0.0375 Output: $0.15 | Model: 0.019 Completion: 4.000 | 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2025-02-27 |
| Command A Translate | command-a-translate-08-2025 | 8K | 8K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2025-08-28 |
| Command R | command-r-08-2024 | 128K | 4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2024-08-30 |
| Command R+ | command-r-plus-08-2024 | 128K | 4K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2024-08-30 |
| Command A Reasoning | command-a-reasoning-08-2025 | 256K | 32K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2025-08-21 |
| Aya Expanse 8B | c4ai-aya-expanse-8b | 8K | 4K | - | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-10-24 |
| Aya Vision 8B | c4ai-aya-vision-8b | 16K | 4K | - | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-04 Updated: 2025-05-14 |
| Aya Vision 32B | c4ai-aya-vision-32b | 16K | 4K | - | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-04 Updated: 2025-05-14 |
| Command R7B | command-r7b-12-2024 | 128K | 4K | Input: $0.0375 Output: $0.15 | Model: 0.019 Completion: 4.000 | 🔧 🌡️ | 2024-06-01 | In: text Out: text | Open Weights Released: 2024-02-27 |
| Command A Vision | command-a-vision-07-2025 | 128K | 8K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🌡️ | 2024-06-01 | In: text, image Out: text | Open Weights Released: 2025-07-31 |
Cortecs¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2 Instruct | kimi-k2-instruct | 131K | 131K | Input: $0.551 Output: $2.646 | Model: 0.276 Completion: 4.802 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-07-11 Updated: 2025-09-05 |
| GLM 4.7 | glm-4p7 | 198K | 198K | Input: $0.45 Output: $2.23 | Model: 0.225 Completion: 4.956 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| Qwen3 Next 80B A3B Thinking | qwen3-next-80b-a3b-thinking | 128K | 128K | Input: $0.164 Output: $1.311 | Model: 0.082 Completion: 7.994 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen3 Coder 480B A35B Instruct | qwen3-coder-480b-a35b-instruct | 262K | 262K | Input: $0.441 Output: $1.984 | Model: 0.221 Completion: 4.499 | 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-07-25 |
| MiniMax-M2.1 | minimax-m2p1 | 196K | 196K | Input: $0.34 Output: $1.34 | Model: 0.170 Completion: 3.941 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| GLM 4.5 Air | glm-4p5-air | 131.1K | 131.1K | Input: $0.22 Output: $1.34 | Model: 0.110 Completion: 6.091 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-08-01 |
| Qwen3 32B | qwen3-32b | 16.4K | 16.4K | Input: $0.099 Output: $0.33 | Model: 0.050 Completion: 3.333 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-04-29 |
| Devstral Small 2 2512 | devstral-small-2512 | 262K | 262K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-12 | In: text, image Out: text | Open Weights Released: 2025-12-09 |
| INTELLECT 3 | intellect-3 | 128K | 128K | Input: $0.219 Output: $1.202 | Model: 0.110 Completion: 5.489 | 📎 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2025-11-26 |
| Nova Pro 1.0 | nova-pro-v1 | 300K | 5K | Input: $1.016 Output: $4.061 | Model: 0.508 Completion: 3.997 | 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2024-12-03 |
| GPT Oss 120b | gpt-oss-120b | 128K | 128K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-01 | In: text Out: text | Open Weights Released: 2025-08-05 |
| DeepSeek V3 0324 | deepseek-v3-0324 | 128K | 128K | Input: $0.551 Output: $1.654 | Model: 0.276 Completion: 3.002 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-03-24 |
| GPT 4.1 | gpt-4.1 | 1M | 32.8K | Input: $2.354 Output: $9.417 | Model: 1.177 Completion: 4.000 | 🔧 🌡️ | 2024-06 | In: text, image Out: text | Released: 2025-04-14 |
| Llama 3.1 405B Instruct | llama-3.1-405b-instruct | 128K | 128K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Devstral 2 2512 | devstral-2512 | 262K | 262K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-12-09 |
| Kimi K2 Thinking | kimi-k2-thinking | 262K | 262K | Input: $0.656 Output: $2.731 | Model: 0.328 Completion: 4.163 | 📎 🧠 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-12-08 |
| GLM 4.5 | glm-4p5 | 131.1K | 131.1K | Input: $0.67 Output: $2.46 | Model: 0.335 Completion: 3.672 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-29 |
| MiniMax-M2 | minimax-m2 | 400K | 400K | Input: $0.39 Output: $1.57 | Model: 0.195 Completion: 4.026 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Open Weights Released: 2025-10-27 |
| Claude Sonnet 4 | claude-sonnet-4 | 200K | 64K | Input: $3.307 Output: $16.536 | Model: 1.653 Completion: 5.000 | 🔧 🌡️ | 2025-03 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude 4.5 Sonnet | claude-4-5-sonnet | 200K | 200K | Input: $3.259 Output: $16.296 | Model: 1.629 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Gemini 2.5 Pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.654 Output: $11.024 | Model: 0.827 Completion: 6.665 | 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-03-20 Updated: 2025-06-17 |
Deep Infra¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-4.7-Flash | zai-org/GLM-4.7-Flash | 202.8K | 16.4K | Input: $0.06 Output: $0.4 | Model: 0.030 Completion: 6.667 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-01-19 |
| GLM-4.7 | zai-org/GLM-4.7 | 202.8K | 16.4K | Input: $0.43 Output: $1.75 Cache Read: $0.08 | Model: 0.215 Completion: 4.070 Cache: 0.186 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-4.5 | zai-org/GLM-4.5 | 131.1K | 98.3K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| MiniMax M2 | MiniMaxAI/MiniMax-M2 | 262.1K | 32.8K | Input: $0.254 Output: $1.02 | Model: 0.127 Completion: 4.016 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-11-13 |
| MiniMax M2.1 | MiniMaxAI/MiniMax-M2.1 | 196.6K | 196.6K | Input: $0.28 Output: $1.2 | Model: 0.140 Completion: 4.286 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-12-23 |
| DeepSeek-R1-0528 | deepseek-ai/DeepSeek-R1-0528 | 163.8K | 64K | Input: $0.5 Output: $2.15 Cache Read: $0.35 | Model: 0.250 Completion: 4.300 Cache: 0.700 | 🧠 🌡️ | 2024-07 | In: text Out: text | Released: 2025-05-28 |
| DeepSeek-V3.2 | deepseek-ai/DeepSeek-V3.2 | 163.8K | 64K | Input: $0.26 Output: $0.38 Cache Read: $0.13 | Model: 0.130 Completion: 1.462 Cache: 0.500 | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2025-12-02 |
| Kimi K2 | moonshotai/Kimi-K2-Instruct | 131.1K | 32.8K | Input: $0.5 Output: $2 | Model: 0.250 Completion: 4.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-11 |
| Kimi K2.5 | moonshotai/Kimi-K2.5 | 262.1K | 32.8K | Input: $0.5 Output: $2.8 | Model: 0.250 Completion: 5.600 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking | moonshotai/Kimi-K2-Thinking | 131.1K | 32.8K | Input: $0.47 Output: $2 | Model: 0.235 Completion: 4.255 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-11-06 Updated: 2025-11-07 |
| Qwen3 Coder 480B A35B Instruct Turbo | Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | 262.1K | 66.5K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen3 Coder 480B A35B Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct | 262.1K | 66.5K | Input: $0.4 Output: $1.6 | Model: 0.200 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 16.4K | Input: $0.05 Output: $0.24 | Model: 0.025 Completion: 4.800 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT OSS 20B | openai/gpt-oss-20b | 131.1K | 16.4K | Input: $0.03 Output: $0.14 | Model: 0.015 Completion: 4.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| Claude Sonnet 3.7 (Latest) | anthropic/claude-3-7-sonnet-latest | 200K | 64K | Input: $3.3 Output: $16.5 Cache Read: $0.33 | Model: 1.650 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-31 | In: text, image Out: text | Released: 2025-03-13 |
| Claude Opus 4 | anthropic/claude-4-opus | 200K | 32K | Input: $16.5 Output: $82.5 | Model: 8.250 Completion: 5.000 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image Out: text | Released: 2025-06-12 |
DeepSeek¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek Reasoner | deepseek-reasoner | 128K | 128K | Input: $0.28 Output: $0.42 Cache Read: $0.028 | Model: 0.140 Completion: 1.500 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-01-20 Updated: 2025-09-29 |
| DeepSeek Chat | deepseek-chat | 128K | 8.2K | Input: $0.28 Output: $0.42 Cache Read: $0.028 | Model: 0.140 Completion: 1.500 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-12-26 Updated: 2025-09-29 |
doubao¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| doubao-seed-1-6-flash | doubao-seed-1-6-flash | 256K | 32K | - | - | 🔧 🌡️ | 2023-10 | In: text, image Out: text | Released: 2025-06-11 Updated: 2025-07-15 |
| doubao-seed-1-6-thinking | doubao-seed-1-6-thinking | 256K | 32K | - | - | 🧠 🔧 🌡️ | 2023-10 | In: text, image Out: text | Released: 2025-06-11 Updated: 2025-07-15 |
| doubao-seed-1-6 | doubao-seed-1-6 | 256K | 32K | - | - | 🧠 🔧 🌡️ | 2023-10 | In: text, image Out: text | Released: 2025-06-11 Updated: 2025-06-15 |
evroc¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Llama 3.3 70B | nvidia/Llama-3.3-70B-Instruct-FP8 | 131.1K | 32.8K | Input: $1.18 Output: $1.18 | Model: 0.590 Completion: 1.000 | 🔧 | - | In: text Out: text | Open Weights Released: 2024-12-01 |
| Phi-4 15B | microsoft/Phi-4-multimodal-instruct | 32K | 32K | Input: $0.24 Output: $0.47 | Model: 0.120 Completion: 1.958 | 🔧 | - | In: text Out: text, image | Open Weights Released: 2025-01-01 |
| E5 Multi-Lingual Large Embeddings 0.6B | intfloat/multilingual-e5-large-instruct | 512 | 512 | Input: $0.12 Output: $0.12 | Model: 0.060 Completion: 1.000 | - | - | In: text Out: text | Open Weights Released: 2024-06-01 |
| Kimi K2.5 | moonshotai/Kimi-K2.5 | 262.1K | 262.1K | Input: $1.47 Output: $5.9 | Model: 0.735 Completion: 4.014 | 🧠 🔧 | - | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| KB Whisper | KBLab/kb-whisper-large | 448 | 448 | Input: $0.00236 Output: $0.00236 Output Audio: $2.36 | Model: 0.001 Completion: 1000.000 | - | - | In: audio Out: text | Open Weights Released: 2024-10-01 |
| Qwen3 30B 2507 | Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 | 64K | 64K | Input: $0.35 Output: $1.42 | Model: 0.175 Completion: 4.057 | 🔧 | - | In: text Out: text | Open Weights Released: 2025-07-30 |
| Qwen3 Embedding 8B | Qwen/Qwen3-Embedding-8B | 41K | 41K | Input: $0.12 Output: $0.12 | Model: 0.060 Completion: 1.000 | - | - | In: text Out: text | Open Weights Released: 2025-07-30 |
| Qwen3 VL 30B | Qwen/Qwen3-VL-30B-A3B-Instruct | 100K | 100K | Input: $0.24 Output: $0.94 | Model: 0.120 Completion: 3.917 | 🔧 | - | In: text, image, video Out: text | Open Weights Released: 2025-07-30 |
| Voxtral Small 24B | mistralai/Voxtral-Small-24B-2507 | 32K | 32K | Input: $0.00236 Output: $0.00236 Output Audio: $2.36 | Model: 0.001 Completion: 1000.000 | - | - | In: audio, text Out: text | Open Weights Released: 2025-03-01 |
| Devstral Small 2 24B Instruct 2512 | mistralai/devstral-small-2-24b-instruct-2512 | 32.8K | 32.8K | Input: $0.12 Output: $0.47 | Model: 0.060 Completion: 3.917 | 🔧 | - | In: text Out: text | Open Weights Released: 2025-12-01 |
| Magistral Small 1.2 24B | mistralai/Magistral-Small-2509 | 131.1K | 131.1K | Input: $0.59 Output: $2.36 | Model: 0.295 Completion: 4.000 | 🔧 | - | In: text Out: text | Open Weights Released: 2025-06-01 |
| GPT OSS 120B | openai/gpt-oss-120b | 65.5K | 65.5K | Input: $0.24 Output: $0.94 | Model: 0.120 Completion: 3.917 | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| Whisper 3 Large | openai/whisper-large-v3 | 448 | 4.1K | Input: $0.00236 Output: $0.00236 Output Audio: $2.36 | Model: 0.001 Completion: 1000.000 | - | - | In: audio Out: text | Open Weights Released: 2024-10-01 |
ExampleCorp AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Novus 1 | novus-1 | 128K | 4.1K | Input: $5 Output: $15 Cache Read: $0.075 Cache Write: $0.5 | Model: 2.500 Completion: 3.000 Cache: 0.015 | 📎 🧠 🔧 🌡️ | 2024-07 | In: text, image, audio, video, pdf Out: text, image, audio, video, pdf | Released: 2025-01-20 Updated: 2025-08-21 |
FastRouter¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek R1 Distill Llama 70B | deepseek-ai/deepseek-r1-distill-llama-70b | 131.1K | 131.1K | Input: $0.03 Output: $0.14 | Model: 0.015 Completion: 4.667 | 🧠 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-01-23 |
| Kimi K2 | moonshotai/kimi-k2 | 131.1K | 32.8K | Input: $0.55 Output: $2.2 | Model: 0.275 Completion: 4.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-11 |
| Gemini 2.5 Flash | google/gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.0375 | Model: 0.150 Completion: 8.333 Cache: 0.125 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, pdf Out: text | Released: 2025-06-17 |
| Gemini 2.5 Pro | google/gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, pdf Out: text | Released: 2025-06-17 |
| Qwen3 Coder | qwen/qwen3-coder | 262.1K | 66.5K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Grok 4 | x-ai/grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 Cache Write: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-09 |
| GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 32.8K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT-4.1 | openai/gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GPT-5 | openai/gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-5 Mini | openai/gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image Out: text | Released: 2025-08-07 |
| GPT OSS 20B | openai/gpt-oss-20b | 131.1K | 65.5K | Input: $0.05 Output: $0.2 | Model: 0.025 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT-5 Nano | openai/gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.005 | Model: 0.025 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image Out: text | Released: 2025-08-07 |
| Claude Opus 4.1 | anthropic/claude-opus-4.1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude Sonnet 4 | anthropic/claude-sonnet-4 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
Fireworks AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2 Instruct | accounts/fireworks/models/kimi-k2-instruct | 128K | 16.4K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-11 |
| GLM 4.7 | accounts/fireworks/models/glm-4p7 | 198K | 198K | Input: $0.6 Output: $2.2 Cache Read: $0.3 | Model: 0.300 Completion: 3.667 Cache: 0.500 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM 5 | accounts/fireworks/models/glm-5 | 202.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.5 | Model: 0.500 Completion: 3.200 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-11 |
| DeepSeek V3.1 | accounts/fireworks/models/deepseek-v3p1 | 163.8K | 163.8K | Input: $0.56 Output: $1.68 | Model: 0.280 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-08-21 |
| MiniMax-M2.1 | accounts/fireworks/models/minimax-m2p1 | 200K | 200K | Input: $0.3 Output: $1.2 Cache Read: $0.03 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| GLM 4.5 Air | accounts/fireworks/models/glm-4p5-air | 131.1K | 131.1K | Input: $0.22 Output: $0.88 | Model: 0.110 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-08-01 |
| DeepSeek V3.2 | accounts/fireworks/models/deepseek-v3p2 | 160K | 160K | Input: $0.56 Output: $1.68 Cache Read: $0.28 | Model: 0.280 Completion: 3.000 Cache: 0.500 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2025-12-01 |
| MiniMax-M2.5 | accounts/fireworks/models/minimax-m2p5 | 196.6K | 196.6K | Input: $0.3 Output: $1.2 Cache Read: $0.03 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| GPT OSS 120B | accounts/fireworks/models/gpt-oss-120b | 131.1K | 32.8K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| Kimi K2.5 | accounts/fireworks/models/kimi-k2p5 | 256K | 256K | Input: $0.6 Output: $3 Cache Read: $0.1 | Model: 0.300 Completion: 5.000 Cache: 0.167 | 🧠 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking | accounts/fireworks/models/kimi-k2-thinking | 256K | 256K | Input: $0.6 Output: $2.5 Cache Read: $0.3 | Model: 0.300 Completion: 4.167 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-11-06 |
| GLM 4.5 | accounts/fireworks/models/glm-4p5 | 131.1K | 131.1K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-29 |
| GPT OSS 20B | accounts/fireworks/models/gpt-oss-20b | 131.1K | 32.8K | Input: $0.05 Output: $0.2 | Model: 0.025 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
Firmware¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.6 | claude-opus-4-6 | 200K | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05-31 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2026-02-17 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 | Model: 0.150 Completion: 8.333 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-07-17 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-12-17 |
| GPT OSS 120B | gpt-oss-120b | 131.1K | 32.8K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 1970-01-01 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-5 | gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Opus 4.5 | claude-opus-4-5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 64K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-11-18 |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| GPT-5 Mini | gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT OSS 20B | gpt-oss-20b | 131.1K | 32.8K | Input: $0.07 Output: $0.2 | Model: 0.035 Completion: 2.857 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 1970-01-01 |
| Gemini 2.5 Pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| GPT-5 Nano | gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.01 | Model: 0.025 Completion: 8.000 Cache: 0.200 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-4o | gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 Updated: 2024-08-06 |
Friendli¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 4.7 | zai-org/GLM-4.7 | 202.8K | 202.8K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-22 Updated: 2026-01-29 |
| GLM 5 | zai-org/GLM-5 | 202.8K | 202.8K | Input: $1 Output: $3.2 | Model: 0.500 Completion: 3.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax M2.1 | MiniMaxAI/MiniMax-M2.1 | 196.6K | 196.6K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-13 Updated: 2026-01-29 |
| Llama 3.1 8B Instruct | meta-llama/Llama-3.1-8B-Instruct | 131.1K | 8K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-01 Updated: 2025-12-23 |
| Llama 3.3 70B Instruct | meta-llama/Llama-3.3-70B-Instruct | 131.1K | 131.1K | Input: $0.6 Output: $0.6 | Model: 0.300 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-01 Updated: 2025-12-23 |
| Qwen3 235B A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262.1K | 262.1K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-29 Updated: 2026-01-29 |
| EXAONE 4.0.1 32B | LGAI-EXAONE/EXAONE-4.0.1-32B | 131.1K | 131.1K | Input: $0.6 Output: $1 | Model: 0.300 Completion: 1.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-31 Updated: 2025-12-23 |
| K EXAONE 236B A23B | LGAI-EXAONE/K-EXAONE-236B-A23B | 262.1K | 262.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-31 Updated: 2026-01-08 |
GitHub Copilot¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.1-Codex-max | gpt-5.1-codex-max | 128K | 128K | Input: $0 Output: $0 | - | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-12-04 |
| GPT-5.2-Codex | gpt-5.2-codex | 272K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| Grok Code Fast 1 | grok-code-fast-1 | 128K | 64K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-08 | In: text Out: text | Released: 2025-08-27 |
| GPT-5.1 | gpt-5.1 | 128K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Claude Sonnet 4.6 | claude-sonnet-4.6 | 128K | 32K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-02-17 |
| Gemini 3 Flash | gemini-3-flash-preview | 128K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video Out: text | Released: 2025-12-17 |
| Claude Haiku 4.5 | claude-haiku-4.5 | 128K | 32K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image Out: text | Released: 2025-10-15 |
| GPT-5.1-Codex-mini | gpt-5.1-codex-mini | 128K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 | gpt-5.2 | 128K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-4.1 | gpt-4.1 | 64K | 16.4K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| Claude Opus 4.5 | claude-opus-4.5 | 128K | 32K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image Out: text | Released: 2025-11-24 Updated: 2025-08-01 |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview | 128K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2026-02-19 |
| GPT-5 | gpt-5 | 128K | 128K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-5.1-Codex | gpt-5.1-codex | 128K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Claude Sonnet 4 | claude-sonnet-4 | 128K | 16K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image Out: text | Released: 2025-05-22 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 128K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video Out: text | Released: 2025-11-18 |
| Claude Sonnet 4.5 | claude-sonnet-4.5 | 128K | 32K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image Out: text | Released: 2025-09-29 |
| GPT-5-mini | gpt-5-mini | 128K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2024-06 | In: text, image Out: text | Released: 2025-08-13 |
| Claude Opus 4.6 | claude-opus-4.6 | 128K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image Out: text | Released: 2026-02-05 |
| Claude Opus 4.1 | claude-opus-41 | 80K | 16K | Input: $0 Output: $0 | - | 📎 🧠 🌡️ | 2025-03-31 | In: text, image Out: text | Released: 2025-08-05 |
| Gemini 2.5 Pro | gemini-2.5-pro | 128K | 64K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-01 | In: text, image, audio, video Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| GPT-4o | gpt-4o | 64K | 16.4K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 |
GitHub Models¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| AI21 Jamba 1.5 Mini | ai21-labs/ai21-jamba-1.5-mini | 256K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2024-08-29 |
| AI21 Jamba 1.5 Large | ai21-labs/ai21-jamba-1.5-large | 256K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2024-08-29 |
| Phi-4-multimodal-instruct | microsoft/phi-4-multimodal-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text, image, audio Out: text | Open Weights Released: 2024-12-11 |
| Phi-3-small instruct (128k) | microsoft/phi-3-small-128k-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Phi-3-medium instruct (128k) | microsoft/phi-3-medium-128k-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| MAI-DS-R1 | microsoft/mai-ds-r1 | 65.5K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Released: 2025-01-20 |
| Phi-3.5-MoE instruct (128k) | microsoft/phi-3.5-moe-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-08-20 |
| Phi-3.5-mini instruct (128k) | microsoft/phi-3.5-mini-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-08-20 |
| Phi-4-mini-instruct | microsoft/phi-4-mini-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| Phi-4 | microsoft/phi-4 | 16K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| Phi-3-mini instruct (4k) | microsoft/phi-3-mini-4k-instruct | 4.1K | 1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Phi-4-mini-reasoning | microsoft/phi-4-mini-reasoning | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| Phi-3.5-vision instruct (128k) | microsoft/phi-3.5-vision-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text, image Out: text | Open Weights Released: 2024-08-20 |
| Phi-3-medium instruct (4k) | microsoft/phi-3-medium-4k-instruct | 4.1K | 1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Phi-3-mini instruct (128k) | microsoft/phi-3-mini-128k-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| Phi-4-Reasoning | microsoft/phi-4-reasoning | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| Phi-3-small instruct (8k) | microsoft/phi-3-small-8k-instruct | 8.2K | 2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-04-23 |
| JAIS 30b Chat | core42/jais-30b-chat | 8.2K | 2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-03 | In: text Out: text | Open Weights Released: 2023-08-30 |
| Ministral 3B | mistral-ai/ministral-3b | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Open Weights Released: 2024-10-22 |
| Mistral Medium 3 (25.05) | mistral-ai/mistral-medium-2505 | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-09 | In: text, image Out: text | Released: 2025-05-01 |
| Mistral Nemo | mistral-ai/mistral-nemo | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Open Weights Released: 2024-07-18 |
| Mistral Large 24.11 | mistral-ai/mistral-large-2411 | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-09 | In: text Out: text | Released: 2024-11-01 |
| Mistral Small 3.1 | mistral-ai/mistral-small-2503 | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-09 | In: text, image Out: text | Released: 2025-03-01 |
| Codestral 25.01 | mistral-ai/codestral-2501 | 32K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2025-01-01 |
| DeepSeek-R1-0528 | deepseek/deepseek-r1-0528 | 65.5K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek-R1 | deepseek/deepseek-r1 | 65.5K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-01-20 |
| DeepSeek-V3-0324 | deepseek/deepseek-v3-0324 | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-03-24 |
| Llama-3.2-90B-Vision-Instruct | meta/llama-3.2-90b-vision-instruct | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text, image, audio Out: text | Open Weights Released: 2024-09-25 |
| Llama-3.3-70B-Instruct | meta/llama-3.3-70b-instruct | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Llama 4 Scout 17B 16E Instruct | meta/llama-4-scout-17b-16e-instruct | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-12 | In: text, image Out: text | Open Weights Released: 2025-01-31 |
| Meta-Llama-3.1-405B-Instruct | meta/meta-llama-3.1-405b-instruct | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Meta-Llama-3-8B-Instruct | meta/meta-llama-3-8b-instruct | 8.2K | 2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-04-18 |
| Llama-3.2-11B-Vision-Instruct | meta/llama-3.2-11b-vision-instruct | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text, image, audio Out: text | Open Weights Released: 2024-09-25 |
| Meta-Llama-3-70B-Instruct | meta/meta-llama-3-70b-instruct | 8.2K | 2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-04-18 |
| Meta-Llama-3.1-70B-Instruct | meta/meta-llama-3.1-70b-instruct | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Meta-Llama-3.1-8B-Instruct | meta/meta-llama-3.1-8b-instruct | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama 4 Maverick 17B 128E Instruct FP8 | meta/llama-4-maverick-17b-128e-instruct-fp8 | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-12 | In: text, image Out: text | Open Weights Released: 2025-01-31 |
| GPT-4o mini | openai/gpt-4o-mini | 128K | 16.4K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-10 | In: text, image, audio Out: text | Released: 2024-07-18 |
| OpenAI o1 | openai/o1 | 200K | 100K | Input: $0 Output: $0 | - | 🧠 | 2023-10 | In: text, image Out: text | Released: 2024-09-12 Updated: 2024-12-17 |
| OpenAI o3 | openai/o3 | 200K | 100K | Input: $0 Output: $0 | - | 🧠 | 2024-04 | In: text, image Out: text | Released: 2025-01-31 |
| GPT-4.1-nano | openai/gpt-4.1-nano | 128K | 16.4K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GPT-4.1 | openai/gpt-4.1 | 128K | 16.4K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| OpenAI o4-mini | openai/o4-mini | 200K | 100K | Input: $0 Output: $0 | - | 🧠 | 2024-04 | In: text, image Out: text | Released: 2025-01-31 |
| GPT-4.1-mini | openai/gpt-4.1-mini | 128K | 16.4K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| OpenAI o1-preview | openai/o1-preview | 128K | 32.8K | Input: $0 Output: $0 | - | 🧠 | 2023-10 | In: text Out: text | Released: 2024-09-12 |
| OpenAI o3-mini | openai/o3-mini | 200K | 100K | Input: $0 Output: $0 | - | 🧠 | 2024-04 | In: text Out: text | Released: 2025-01-31 |
| OpenAI o1-mini | openai/o1-mini | 128K | 65.5K | Input: $0 Output: $0 | - | 🧠 | 2023-10 | In: text Out: text | Released: 2024-09-12 Updated: 2024-12-17 |
| GPT-4o | openai/gpt-4o | 128K | 16.4K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-10 | In: text, image, audio Out: text | Released: 2024-05-13 |
| Cohere Command A | cohere/cohere-command-a | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2024-11-01 |
| Cohere Command R+ 08-2024 | cohere/cohere-command-r-plus-08-2024 | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2024-08-01 |
| Cohere Command R | cohere/cohere-command-r | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2024-03-11 Updated: 2024-08-01 |
| Cohere Command R 08-2024 | cohere/cohere-command-r-08-2024 | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2024-08-01 |
| Cohere Command R+ | cohere/cohere-command-r-plus | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-03 | In: text Out: text | Released: 2024-04-04 Updated: 2024-08-01 |
| Grok 3 | xai/grok-3 | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12-09 |
| Grok 3 Mini | xai/grok-3-mini | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12-09 |
GitLab Duo¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Agentic Chat (GPT-5.2 Codex) | duo-chat-gpt-5-2-codex | 400K | 128K | Input: $0 Output: $0 | - | 📎 🧠 🔧 | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-01-22 |
| Agentic Chat (Claude Opus 4.6) | duo-chat-opus-4-6 | 200K | 64K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Agentic Chat (GPT-5 Mini) | duo-chat-gpt-5-mini | 400K | 128K | Input: $0 Output: $0 | - | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2026-01-22 |
| Agentic Chat (Claude Sonnet 4.5) | duo-chat-sonnet-4-5 | 200K | 64K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2026-01-08 |
| Agentic Chat (Claude Haiku 4.5) | duo-chat-haiku-4-5 | 200K | 64K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2026-01-08 |
| Agentic Chat (GPT-5 Codex) | duo-chat-gpt-5-codex | 400K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2026-01-22 |
| Agentic Chat (GPT-5.2) | duo-chat-gpt-5-2 | 400K | 128K | Input: $0 Output: $0 | - | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2026-01-23 |
| Agentic Chat (Claude Sonnet 4.6) | duo-chat-sonnet-4-6 | 200K | 64K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 📎 🧠 🔧 🌡️ | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Agentic Chat (Claude Opus 4.5) | duo-chat-opus-4-5 | 200K | 64K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2026-01-08 |
| Agentic Chat (GPT-5.1) | duo-chat-gpt-5-1 | 400K | 128K | Input: $0 Output: $0 | - | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2026-01-22 |
Google¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| gemini-embedding-001 | gemini-embedding-001 | 2K | 3.1K | Input: $0.15 Output: $0 Cache Read: $0 Cache Write: $0 | Model: 0.075 | 🔧 | 2025-06 | In: text Out: text | Released: 2025-06-01 |
| Gemini 2.5 Flash Lite Preview 09-25 | gemini-2.5-flash-lite-preview-09-2025 | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 3.1 Pro Preview Custom Tools | gemini-3.1-pro-preview-customtools | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2026-02-19 |
| Gemini 2.5 Pro Preview 06-05 | gemini-2.5-pro-preview-06-05 | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-05 |
| Gemini 2.5 Flash Preview 04-17 | gemini-2.5-flash-preview-04-17 | 1M | 65.5K | Input: $0.15 Output: $0.6 Cache Read: $0.0375 | Model: 0.075 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-04-17 |
| Gemini 2.5 Flash Preview 09-25 | gemini-2.5-flash-preview-09-2025 | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Input Audio: $1 | Model: 0.500 Completion: 2.500 Cache: 0.075 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Pro Preview 05-06 | gemini-2.5-pro-preview-05-06 | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-05-06 |
| Gemini 2.5 Flash Preview 05-20 | gemini-2.5-flash-preview-05-20 | 1M | 65.5K | Input: $0.15 Output: $0.6 Cache Read: $0.0375 | Model: 0.075 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-05-20 |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Input Audio: $1 | Model: 0.500 Completion: 2.500 Cache: 0.075 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| Gemini Live 2.5 Flash | gemini-live-2.5-flash | 128K | 8K | Input: $0.5 Output: $2 Input Audio: $3 Output Audio: $12 | Model: 1.500 Completion: 4.000 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video Out: text, audio | Released: 2025-09-01 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-12-17 |
| Gemini Live 2.5 Flash Preview Native Audio | gemini-live-2.5-flash-preview-native-audio | 131.1K | 65.5K | Input: $0.5 Output: $2 Input Audio: $3 Output Audio: $12 | Model: 1.500 Completion: 4.000 | 🧠 🔧 | 2025-01 | In: text, audio, video Out: text, audio | Released: 2025-06-17 Updated: 2025-09-18 |
| Gemini 2.5 Flash-Lite | gemini-2.5-flash-lite | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 2.5 Flash Preview TTS | gemini-2.5-flash-preview-tts | 8K | 16K | Input: $0.5 Output: $10 | Model: 0.250 Completion: 20.000 | - | 2025-01 | In: text Out: audio | Released: 2025-05-01 |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2026-02-19 |
| Gemini Flash Latest | gemini-flash-latest | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Input Audio: $1 | Model: 0.500 Completion: 2.500 Cache: 0.075 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Flash Lite Preview 06-17 | gemini-2.5-flash-lite-preview-06-17 | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 Input Audio: $0.3 | Model: 0.150 Completion: 1.333 Cache: 0.083 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 2.5 Flash Image | gemini-2.5-flash-image | 32.8K | 32.8K | Input: $0.3 Output: $30 Cache Read: $0.075 | Model: 0.150 Completion: 100.000 Cache: 0.250 | 📎 🧠 🌡️ | 2025-06 | In: text, image Out: text, image | Released: 2025-08-26 |
| Gemini 2.5 Pro Preview TTS | gemini-2.5-pro-preview-tts | 8K | 16K | Input: $1 Output: $20 | Model: 0.500 Completion: 20.000 | - | 2025-01 | In: text Out: audio | Released: 2025-05-01 |
| Gemini 2.5 Flash Image (Preview) | gemini-2.5-flash-image-preview | 32.8K | 32.8K | Input: $0.3 Output: $30 Cache Read: $0.075 | Model: 0.150 Completion: 100.000 Cache: 0.250 | 📎 🧠 🌡️ | 2025-06 | In: text, image Out: text, image | Released: 2025-08-26 |
| Gemini 1.5 Flash-8B | gemini-1.5-flash-8b | 1M | 8.2K | Input: $0.0375 Output: $0.15 Cache Read: $0.01 | Model: 0.019 Completion: 4.000 Cache: 0.267 | 📎 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text | Released: 2024-10-03 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 64K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-11-18 |
| Gemini 2.0 Flash Lite | gemini-2.0-flash-lite | 1M | 8.2K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 📎 🔧 🌡️ | 2024-06 | In: text, image, audio, video, pdf Out: text | Released: 2024-12-11 |
| Gemini 1.5 Flash | gemini-1.5-flash | 1M | 8.2K | Input: $0.075 Output: $0.3 Cache Read: $0.01875 | Model: 0.037 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text | Released: 2024-05-14 |
| Gemini Flash-Lite Latest | gemini-flash-lite-latest | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| Gemini 2.0 Flash | gemini-2.0-flash | 1M | 8.2K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-06 | In: text, image, audio, video, pdf Out: text | Released: 2024-12-11 |
| Gemini 1.5 Pro | gemini-1.5-pro | 1M | 8.2K | Input: $1.25 Output: $5 Cache Read: $0.3125 | Model: 0.625 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text | Released: 2024-02-15 |
Vertex¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Gemini Embedding 001 | gemini-embedding-001 | 2K | 3.1K | Input: $0.15 Output: $0 | Model: 0.075 | - | 2025-05 | In: text Out: text | Released: 2025-05-20 |
| Gemini 2.5 Flash Lite Preview 09-25 | gemini-2.5-flash-lite-preview-09-2025 | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 3.1 Pro Preview Custom Tools | gemini-3.1-pro-preview-customtools | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2026-02-19 |
| Gemini 2.5 Pro Preview 06-05 | gemini-2.5-pro-preview-06-05 | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-05 |
| Gemini 2.5 Flash Preview 04-17 | gemini-2.5-flash-preview-04-17 | 1M | 65.5K | Input: $0.15 Output: $0.6 Cache Read: $0.0375 | Model: 0.075 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-04-17 |
| Gemini 2.5 Flash Preview 09-25 | gemini-2.5-flash-preview-09-2025 | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Cache Write: $0.383 | Model: 0.150 Completion: 8.333 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Pro Preview 05-06 | gemini-2.5-pro-preview-05-06 | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-05-06 |
| Gemini 2.5 Flash Preview 05-20 | gemini-2.5-flash-preview-05-20 | 1M | 65.5K | Input: $0.15 Output: $0.6 Cache Read: $0.0375 | Model: 0.075 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-05-20 |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Cache Write: $0.383 | Model: 0.150 Completion: 8.333 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-12-17 |
| Gemini 2.5 Flash Lite | gemini-2.5-flash-lite | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2026-02-19 |
| Gemini Flash Latest | gemini-flash-latest | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Cache Write: $0.383 | Model: 0.150 Completion: 8.333 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Flash Lite Preview 06-17 | gemini-2.5-flash-lite-preview-06-17 | 65.5K | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-11-18 |
| Gemini 2.0 Flash Lite | gemini-2.0-flash-lite | 1M | 8.2K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 📎 🔧 🌡️ | 2024-06 | In: text, image, audio, video, pdf Out: text | Released: 2024-12-11 |
| Gemini Flash-Lite Latest | gemini-flash-lite-latest | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| Gemini 2.0 Flash | gemini-2.0-flash | 1M | 8.2K | Input: $0.15 Output: $0.6 Cache Read: $0.025 | Model: 0.075 Completion: 4.000 Cache: 0.167 | 📎 🔧 🌡️ | 2024-06 | In: text, image, audio, video, pdf Out: text | Released: 2024-12-11 |
| GLM-5 | zai-org/glm-5-maas | 204.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.1 | Model: 0.500 Completion: 3.200 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-11 |
| GLM-4.7 | zai-org/glm-4.7-maas | 200K | 128K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | 2025-04 | In: text, pdf Out: text | Open Weights Released: 2026-01-06 |
| DeepSeek V3.1 | deepseek-ai/deepseek-v3.1-maas | 163.8K | 32.8K | Input: $0.6 Output: $1.7 | Model: 0.300 Completion: 2.833 | 🧠 🔧 🌡️ | - | In: text, pdf Out: text | Open Weights Released: 2025-08-28 |
| Qwen3 235B A22B Instruct | qwen/qwen3-235b-a22b-instruct-2507-maas | 262.1K | 16.4K | Input: $0.22 Output: $0.88 | Model: 0.110 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-13 |
| Llama 4 Maverick 17B 128E Instruct | meta/llama-4-maverick-17b-128e-instruct-maas | 524.3K | 8.2K | Input: $0.35 Output: $1.15 | Model: 0.175 Completion: 3.286 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-29 |
| Llama 3.3 70B Instruct | meta/llama-3.3-70b-instruct-maas | 128K | 8.2K | Input: $0.72 Output: $0.72 | Model: 0.360 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-04-29 |
| GPT OSS 20B | openai/gpt-oss-20b-maas | 131.1K | 32.8K | Input: $0.07 Output: $0.25 | Model: 0.035 Completion: 3.571 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT OSS 120B | openai/gpt-oss-120b-maas | 131.1K | 32.8K | Input: $0.09 Output: $0.36 | Model: 0.045 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
Vertex (Anthropic)¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4.5 | claude-sonnet-4-5@20250929 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Claude Opus 4.1 | claude-opus-4-1@20250805 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude Sonnet 3.7 | claude-3-7-sonnet@20250219 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-31 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Opus 4 | claude-opus-4@20250514 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Opus 4.5 | claude-opus-4-5@20251101 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Claude Haiku 3.5 | claude-3-5-haiku@20241022 | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Sonnet 4 | claude-sonnet-4@20250514 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 3.5 v2 | claude-3-5-sonnet@20241022 | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04-30 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Opus 4.6 | claude-opus-4-6@default | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Claude Haiku 4.5 | claude-haiku-4-5@20251001 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Sonnet 4.6 | claude-sonnet-4-6@default | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
Groq¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Llama 3 70B | llama3-70b-8192 | 8.2K | 8.2K | Input: $0.59 Output: $0.79 | Model: 0.295 Completion: 1.339 | 🔧 🌡️ | 2023-03 | In: text Out: text | Open Weights Released: 2024-04-18 |
| Qwen QwQ 32B | qwen-qwq-32b | 131.1K | 16.4K | Input: $0.29 Output: $0.39 | Model: 0.145 Completion: 1.345 | 🧠 🔧 🌡️ | 2024-09 | In: text Out: text | Open Weights Released: 2024-11-27 |
| Llama 3.1 8B Instant | llama-3.1-8b-instant | 131.1K | 131.1K | Input: $0.05 Output: $0.08 | Model: 0.025 Completion: 1.600 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama Guard 3 8B | llama-guard-3-8b | 8.2K | 8.2K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-23 |
| DeepSeek R1 Distill Llama 70B | deepseek-r1-distill-llama-70b | 131.1K | 8.2K | Input: $0.75 Output: $0.99 | Model: 0.375 Completion: 1.320 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-01-20 |
| Llama 3 8B | llama3-8b-8192 | 8.2K | 8.2K | Input: $0.05 Output: $0.08 | Model: 0.025 Completion: 1.600 | 🔧 🌡️ | 2023-03 | In: text Out: text | Open Weights Released: 2024-04-18 |
| Mistral Saba 24B | mistral-saba-24b | 32.8K | 32.8K | Input: $0.79 Output: $0.79 | Model: 0.395 Completion: 1.000 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2025-02-06 |
| Llama 3.3 70B Versatile | llama-3.3-70b-versatile | 131.1K | 32.8K | Input: $0.59 Output: $0.79 | Model: 0.295 Completion: 1.339 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Gemma 2 9B | gemma2-9b-it | 8.2K | 8.2K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🔧 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2024-06-27 |
| Kimi K2 Instruct | moonshotai/kimi-k2-instruct | 131.1K | 16.4K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-14 |
| Kimi K2 Instruct 0905 | moonshotai/kimi-k2-instruct-0905 | 262.1K | 16.4K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Qwen3 32B | qwen/qwen3-32b | 131.1K | 16.4K | Input: $0.29 Output: $0.59 | Model: 0.145 Completion: 2.034 | 🧠 🔧 🌡️ | 2024-11-08 | In: text Out: text | Open Weights Released: 2024-12-23 |
| Llama 4 Scout 17B | meta-llama/llama-4-scout-17b-16e-instruct | 131.1K | 8.2K | Input: $0.11 Output: $0.34 | Model: 0.055 Completion: 3.091 | 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Llama Guard 4 12B | meta-llama/llama-guard-4-12b | 131.1K | 1K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Llama 4 Maverick 17B | meta-llama/llama-4-maverick-17b-128e-instruct | 131.1K | 8.2K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 65.5K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT OSS 20B | openai/gpt-oss-20b | 131.1K | 65.5K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
Helicone¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Anthropic: Claude 4.5 Haiku | claude-4.5-haiku | 200K | 8.2K | Input: $1 Output: $5 Cache Read: $0.09999999999999999 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 🔧 🌡️ | 2025-10 | In: text, image Out: text | Released: 2025-10-01 |
| OpenAI: GPT-5 Codex | gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.12500000000000003 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text Out: text | Released: 2025-01-01 |
| OpenAI: GPT-5 Pro | gpt-5-pro | 128K | 32.8K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | - | 2025-01 | In: text Out: text | Released: 2025-01-01 |
| DeepSeek Reasoner | deepseek-reasoner | 128K | 64K | Input: $0.56 Output: $1.68 Cache Read: $0.07 | Model: 0.280 Completion: 3.000 Cache: 0.125 | 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-20 |
| Anthropic: Claude 3.7 Sonnet | claude-3.7-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.30000000000000004 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 🔧 🌡️ | 2025-02 | In: text, image Out: text | Released: 2025-02-19 |
| OpenAI GPT-4o-mini | gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.075 | Model: 0.075 Completion: 4.000 Cache: 0.500 | 🔧 🌡️ | 2024-07 | In: text, image Out: text | Released: 2024-07-18 |
| xAI: Grok 4 Fast Reasoning | grok-4-fast-reasoning | 2M | 2M | Input: $0.19999999999999998 Output: $0.5 Cache Read: $0.049999999999999996 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-09 | In: text, image Out: text | Released: 2025-09-01 |
| OpenAI GPT-5 Chat Latest | gpt-5-chat-latest | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.12500000000000003 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🔧 | 2024-09 | In: text, image Out: text | Released: 2024-09-30 |
| Meta Llama 4 Scout 17B 16E | llama-4-scout | 131.1K | 8.2K | Input: $0.08 Output: $0.3 | Model: 0.040 Completion: 3.750 | 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-01-01 |
| OpenAI Codex Mini Latest | codex-mini-latest | 200K | 100K | Input: $1.5 Output: $6 Cache Read: $0.375 | Model: 0.750 Completion: 4.000 Cache: 0.250 | 🔧 | 2025-01 | In: text, image Out: text | Released: 2025-01-01 |
| Qwen2.5 Coder 7B fast | qwen2.5-coder-7b-fast | 32K | 8.2K | Input: $0.03 Output: $0.09 | Model: 0.015 Completion: 3.000 | 🌡️ | 2024-09 | In: text Out: text | Released: 2024-09-15 |
| Anthropic: Claude Opus 4.1 | claude-opus-4-1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-08 | In: text, image Out: text | Released: 2025-08-05 |
| Perplexity Sonar Reasoning Pro | sonar-reasoning-pro | 127K | 4.1K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 🧠 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-27 |
| DeepSeek V3 | deepseek-v3 | 128K | 8.2K | Input: $0.56 Output: $1.68 Cache Read: $0.07 | Model: 0.280 Completion: 3.000 Cache: 0.125 | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2024-12-26 |
| Meta Llama 3.1 8B Instruct Turbo | llama-3.1-8b-instruct-turbo | 128K | 128K | Input: $0.02 Output: $0.03 | Model: 0.010 Completion: 1.500 | 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-07-23 |
| xAI Grok 3 | grok-3 | 131.1K | 131.1K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-06 | In: text Out: text | Released: 2024-06-01 |
| Baidu Ernie 4.5 21B A3B Thinking | ernie-4.5-21b-a3b-thinking | 128K | 8K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🧠 🌡️ | 2025-03 | In: text Out: text | Released: 2025-03-16 |
| xAI Grok Code Fast 1 | grok-code-fast-1 | 256K | 10K | Input: $0.19999999999999998 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-08-25 |
| Meta Llama Prompt Guard 2 22M | llama-prompt-guard-2-22m | 512 | 2 | Input: $0.01 Output: $0.01 | Model: 0.005 Completion: 1.000 | 🌡️ | 2024-10 | In: text Out: text | Released: 2024-10-01 |
| Meta Llama 3.3 70B Instruct | llama-3.3-70b-instruct | 128K | 16.4K | Input: $0.13 Output: $0.39 | Model: 0.065 Completion: 3.000 | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2024-12-06 |
| xAI Grok 4.1 Fast Reasoning | grok-4-1-fast-reasoning | 2M | 2M | Input: $0.19999999999999998 Output: $0.5 Cache Read: $0.049999999999999996 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-11 | In: text, image Out: text | Released: 2025-11-17 |
| Anthropic: Claude Sonnet 4.5 | claude-4.5-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.30000000000000004 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-09 | In: text, image Out: text | Released: 2025-09-29 |
| OpenAI GPT-4.1 Mini | gpt-4.1-mini-2025-04-14 | 1M | 32.8K | Input: $0.39999999999999997 Output: $1.5999999999999999 Cache Read: $0.09999999999999999 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 🔧 🌡️ | 2025-04 | In: text, image Out: text | Released: 2025-04-14 |
| Google Gemini 2.5 Flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Cache Write: $0.3 | Model: 0.150 Completion: 8.333 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-06-17 |
| Meta Llama Guard 4 12B | llama-guard-4 | 131.1K | 1K | Input: $0.21 Output: $0.21 | Model: 0.105 Completion: 1.000 | 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-01-01 |
| xAI Grok 4.1 Fast Non-Reasoning | grok-4-1-fast-non-reasoning | 2M | 30K | Input: $0.19999999999999998 Output: $0.5 Cache Read: $0.049999999999999996 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🔧 🌡️ | 2025-11 | In: text, image Out: text, image | Released: 2025-11-17 |
| OpenAI: o1 | o1 | 200K | 100K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | - | 2025-01 | In: text Out: text | Released: 2025-01-01 |
| OpenAI GPT-5.1 | gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.12500000000000003 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text, image Out: text, image | Released: 2025-01-01 |
| Kimi K2 (09/05) | kimi-k2-0905 | 262.1K | 16.4K | Input: $0.5 Output: $2 Cache Read: $0.39999999999999997 | Model: 0.250 Completion: 4.000 Cache: 0.800 | 🔧 🌡️ | 2025-09 | In: text Out: text | Released: 2025-09-05 |
| xAI Grok 4 | grok-4 | 256K | 256K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-07-09 |
| Meta Llama 3.1 8B Instant | llama-3.1-8b-instant | 131.1K | 32.7K | Input: $0.049999999999999996 Output: $0.08 | Model: 0.025 Completion: 1.600 | 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-07-01 |
| Perplexity Sonar | sonar | 127K | 4.1K | Input: $1 Output: $1 | Model: 0.500 Completion: 1.000 | 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-27 |
| OpenAI o3 | o3 | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 🔧 | 2024-06 | In: text, image Out: text | Released: 2024-06-01 |
| Qwen3 Coder 480B A35B Instruct Turbo | qwen3-coder | 262.1K | 16.4K | Input: $0.22 Output: $0.95 | Model: 0.110 Completion: 4.318 | 🔧 🌡️ | 2025-07 | In: text, image, audio, video Out: text | Released: 2025-07-23 |
| Zai GLM-4.6 | glm-4.6 | 204.8K | 131.1K | Input: $0.44999999999999996 Output: $1.5 | Model: 0.225 Completion: 3.333 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-07-18 |
| Perplexity Sonar Reasoning | sonar-reasoning | 127K | 4.1K | Input: $1 Output: $5 | Model: 0.500 Completion: 5.000 | 🧠 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-27 |
| Qwen3 32B | qwen3-32b | 131.1K | 41K | Input: $0.29 Output: $0.59 | Model: 0.145 Completion: 2.034 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04-28 |
| Perplexity Sonar Deep Research | sonar-deep-research | 127K | 4.1K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 🧠 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-27 |
| OpenAI GPT-4.1 Nano | gpt-4.1-nano | 1M | 32.8K | Input: $0.09999999999999999 Output: $0.39999999999999997 Cache Read: $0.024999999999999998 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 🔧 🌡️ | 2025-04 | In: text, image Out: text | Released: 2025-04-14 |
| Anthropic: Claude Sonnet 4.5 (20250929) | claude-sonnet-4-5-20250929 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.30000000000000004 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-09 | In: text, image Out: text | Released: 2025-09-29 |
| Google Gemini 2.5 Flash Lite | gemini-2.5-flash-lite | 1M | 65.5K | Input: $0.09999999999999999 Output: $0.39999999999999997 Cache Read: $0.024999999999999998 Cache Write: $0.09999999999999999 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-07-22 |
| Anthropic: Claude 3.5 Haiku | claude-3.5-haiku | 200K | 8.2K | Input: $0.7999999999999999 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-10-22 |
| OpenAI GPT-OSS 120b | gpt-oss-120b | 131.1K | 131.1K | Input: $0.04 Output: $0.16 | Model: 0.020 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Released: 2024-06-01 |
| OpenAI: GPT-5.1 Codex Mini | gpt-5.1-codex-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.024999999999999998 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text, image Out: text, image | Released: 2025-01-01 |
| DeepSeek R1 Distill Llama 70B | deepseek-r1-distill-llama-70b | 128K | 4.1K | Input: $0.03 Output: $0.13 | Model: 0.015 Completion: 4.333 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-20 |
| DeepSeek V3.1 Terminus | deepseek-v3.1-terminus | 128K | 16.4K | Input: $0.27 Output: $1 Cache Read: $0.21600000000000003 | Model: 0.135 Completion: 3.704 Cache: 0.800 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Released: 2025-09-22 |
| OpenAI GPT-4.1 | gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 🔧 🌡️ | 2025-04 | In: text, image Out: text | Released: 2025-04-14 |
| Anthropic: Claude 3.5 Sonnet v2 | claude-3.5-sonnet-v2 | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.30000000000000004 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-10-22 |
| Mistral Small | mistral-small | 128K | 128K | Input: $75 Output: $200 | Model: 37.500 Completion: 2.667 | 🌡️ | 2024-02 | In: text, image Out: text | Released: 2024-02-26 |
| OpenAI o3 Pro | o3-pro | 200K | 100K | Input: $20 Output: $80 | Model: 10.000 Completion: 4.000 | 🔧 | 2024-06 | In: text, image Out: text | Released: 2024-06-01 |
| Mistral Nemo | mistral-nemo | 128K | 16.4K | Input: $20 Output: $40 | Model: 10.000 Completion: 2.000 | 🌡️ | 2024-07 | In: text, image Out: text | Released: 2024-07-18 |
| Qwen3 Coder 30B A3B Instruct | qwen3-coder-30b-a3b-instruct | 262.1K | 262.1K | Input: $0.09999999999999999 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-31 |
| Qwen3 VL 235B A22B Instruct | qwen3-vl-235b-a22b-instruct | 256K | 16.4K | Input: $0.3 Output: $1.5 | Model: 0.150 Completion: 5.000 | 🔧 🌡️ | 2025-09 | In: text, image, video Out: text | Released: 2025-09-23 |
| Qwen3 235B A22B Thinking | qwen3-235b-a22b-thinking | 262.1K | 81.9K | Input: $0.3 Output: $2.9000000000000004 | Model: 0.150 Completion: 9.667 | 🧠 🌡️ | 2025-07 | In: text, image, video Out: text | Released: 2025-07-25 |
| DeepSeek V3.2 | deepseek-v3.2 | 163.8K | 65.5K | Input: $0.27 Output: $0.41 | Model: 0.135 Completion: 1.519 | 🔧 🌡️ | 2025-09 | In: text Out: text | Released: 2025-09-22 |
| xAI Grok 3 Mini | grok-3-mini | 131.1K | 131.1K | Input: $0.3 Output: $0.5 Cache Read: $0.075 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🔧 🌡️ | 2024-06 | In: text Out: text | Released: 2024-06-01 |
| Anthropic: Claude 3 Haiku | claude-3-haiku-20240307 | 200K | 4.1K | Input: $0.25 Output: $1.25 Cache Read: $0.03 Cache Write: $0.3 | Model: 0.125 Completion: 5.000 Cache: 0.120 | 🔧 🌡️ | 2024-03 | In: text, image Out: text | Released: 2024-03-07 |
| Anthropic: Claude 4.5 Haiku (20251001) | claude-haiku-4-5-20251001 | 200K | 8.2K | Input: $1 Output: $5 Cache Read: $0.09999999999999999 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 🔧 🌡️ | 2025-10 | In: text, image Out: text | Released: 2025-10-01 |
| Kimi K2 (07/11) | kimi-k2-0711 | 131.1K | 16.4K | Input: $0.5700000000000001 Output: $2.3 | Model: 0.285 Completion: 4.035 | 🔧 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-01 |
| OpenAI GPT-5 | gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.12500000000000003 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text, image Out: text | Released: 2025-01-01 |
| OpenAI o4 Mini | o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.275 | Model: 0.550 Completion: 4.000 Cache: 0.250 | 🔧 | 2024-06 | In: text, image Out: text | Released: 2024-06-01 |
| OpenAI GPT-4.1 Mini | gpt-4.1-mini | 1M | 32.8K | Input: $0.39999999999999997 Output: $1.5999999999999999 Cache Read: $0.09999999999999999 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 🔧 🌡️ | 2025-04 | In: text, image Out: text | Released: 2025-04-14 |
| Meta Llama 3.3 70B Versatile | llama-3.3-70b-versatile | 131.1K | 32.7K | Input: $0.59 Output: $0.7899999999999999 | Model: 0.295 Completion: 1.339 | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2024-12-06 |
| Meta Llama 4 Maverick 17B 128E | llama-4-maverick | 131.1K | 8.2K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-01-01 |
| Kimi K2 Thinking | kimi-k2-thinking | 256K | 262.1K | Input: $0.48 Output: $2 | Model: 0.240 Completion: 4.167 | 🔧 🌡️ | 2025-11 | In: text Out: text | Released: 2025-11-06 |
| Google Gemma 2 | gemma2-9b-it | 8.2K | 8.2K | Input: $0.01 Output: $0.03 | Model: 0.005 Completion: 3.000 | 🌡️ | 2024-06 | In: text Out: text | Released: 2024-06-25 |
| DeepSeek TNG R1T2 Chimera | deepseek-tng-r1t2-chimera | 130K | 163.8K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-02 |
| Perplexity Sonar Pro | sonar-pro | 200K | 4.1K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 🌡️ | 2025-01 | In: text Out: text | Released: 2025-01-27 |
| Anthropic: Claude Opus 4 | claude-opus-4 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-05-14 |
| OpenAI: GPT-5.1 Codex | gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.12500000000000003 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text, image Out: text, image | Released: 2025-01-01 |
| Mistral-Large | mistral-large-2411 | 128K | 32.8K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-07-24 |
| Anthropic: Claude Opus 4.5 | claude-4.5-opus | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-11 | In: text, image Out: text | Released: 2025-11-24 |
| OpenAI ChatGPT-4o | chatgpt-4o-latest | 128K | 16.4K | Input: $5 Output: $20 Cache Read: $2.5 | Model: 2.500 Completion: 4.000 Cache: 0.500 | 🔧 🌡️ | 2024-08 | In: text, image Out: text | Released: 2024-08-14 |
| Meta Llama 3.1 8B Instruct | llama-3.1-8b-instruct | 16.4K | 16.4K | Input: $0.02 Output: $0.049999999999999996 | Model: 0.010 Completion: 2.500 | 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-07-23 |
| Anthropic: Claude Sonnet 4 | claude-sonnet-4 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.30000000000000004 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-05-14 |
| Google Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.19999999999999998 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-11 | In: text, image, audio, video Out: text | Released: 2025-11-18 |
| Qwen3 Next 80B A3B Instruct | qwen3-next-80b-a3b-instruct | 262K | 16.4K | Input: $0.14 Output: $1.4 | Model: 0.070 Completion: 10.000 | 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Released: 2025-01-01 |
| Meta Llama Prompt Guard 2 86M | llama-prompt-guard-2-86m | 512 | 2 | Input: $0.01 Output: $0.01 | Model: 0.005 Completion: 1.000 | 🌡️ | 2024-10 | In: text Out: text | Released: 2024-10-01 |
| OpenAI o3 Mini | o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🔧 | 2023-10 | In: text Out: text | Released: 2023-10-01 |
| Google Gemma 3 12B | gemma-3-12b-it | 131.1K | 8.2K | Input: $0.049999999999999996 Output: $0.09999999999999999 | Model: 0.025 Completion: 2.000 | 🌡️ | 2024-12 | In: text, image Out: text | Released: 2024-12-01 |
| Qwen3 30B A3B | qwen3-30b-a3b | 41K | 41K | Input: $0.08 Output: $0.29 | Model: 0.040 Completion: 3.625 | 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-06-01 |
| xAI Grok 4 Fast Non-Reasoning | grok-4-fast-non-reasoning | 2M | 2M | Input: $0.19999999999999998 Output: $0.5 Cache Read: $0.049999999999999996 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🔧 🌡️ | 2025-09 | In: text, image, audio Out: text | Released: 2025-09-19 |
| OpenAI GPT-5 Mini | gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.024999999999999998 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text, image Out: text | Released: 2025-01-01 |
| OpenAI GPT-OSS 20b | gpt-oss-20b | 131.1K | 131.1K | Input: $0.049999999999999996 Output: $0.19999999999999998 | Model: 0.025 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Released: 2024-06-01 |
| Hermes 2 Pro Llama 3 8B | hermes-2-pro-llama-3-8b | 131.1K | 131.1K | Input: $0.14 Output: $0.14 | Model: 0.070 Completion: 1.000 | 🔧 🌡️ | 2024-05 | In: text Out: text | Released: 2024-05-27 |
| OpenAI GPT-5.1 Chat | gpt-5.1-chat-latest | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.12500000000000003 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text, image Out: text, image | Released: 2025-01-01 |
| Anthropic: Claude Opus 4.1 (20250805) | claude-opus-4-1-20250805 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-08 | In: text, image Out: text | Released: 2025-08-05 |
| Google Gemini 2.5 Pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.3125 Cache Write: $1.25 | Model: 0.625 Completion: 8.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-06 | In: text, image Out: text | Released: 2025-06-17 |
| OpenAI GPT-5 Nano | gpt-5-nano | 400K | 128K | Input: $0.049999999999999996 Output: $0.39999999999999997 Cache Read: $0.005 | Model: 0.025 Completion: 8.000 Cache: 0.100 | 🔧 | 2025-01 | In: text, image Out: text | Released: 2025-01-01 |
| OpenAI: o1-mini | o1-mini | 128K | 65.5K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | - | 2025-01 | In: text Out: text | Released: 2025-01-01 |
| OpenAI GPT-4o | gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 🔧 🌡️ | 2024-05 | In: text, image Out: text | Released: 2024-05-13 |
Hugging Face¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-4.7-Flash | zai-org/GLM-4.7-Flash | 200K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-08-08 |
| GLM-4.7 | zai-org/GLM-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.11 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-5 | zai-org/GLM-5 | 202.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-11 |
| MiMo-V2-Flash | XiaomiMiMo/MiMo-V2-Flash | 262.1K | 4.1K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-12-16 |
| MiniMax-M2.5 | MiniMaxAI/MiniMax-M2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax-M2.1 | MiniMaxAI/MiniMax-M2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-10 | In: text Out: text | Open Weights Released: 2025-12-23 |
| DeepSeek-R1-0528 | deepseek-ai/DeepSeek-R1-0528 | 163.8K | 163.8K | Input: $3 Output: $5 | Model: 1.500 Completion: 1.667 | 🧠 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek-V3.2 | deepseek-ai/DeepSeek-V3.2 | 163.8K | 65.5K | Input: $0.28 Output: $0.4 | Model: 0.140 Completion: 1.429 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| Kimi-K2-Instruct | moonshotai/Kimi-K2-Instruct | 131.1K | 16.4K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-14 |
| Kimi-K2-Instruct-0905 | moonshotai/Kimi-K2-Instruct-0905 | 262.1K | 16.4K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-04 |
| Kimi-K2.5 | moonshotai/Kimi-K2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 Cache Read: $0.1 | Model: 0.300 Completion: 5.000 Cache: 0.167 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01-01 |
| Kimi-K2-Thinking | moonshotai/Kimi-K2-Thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Qwen3-Next-80B-A3B-Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | 262.1K | 66.5K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen3.5-397B-A17B | Qwen/Qwen3.5-397B-A17B | 262.1K | 32.8K | Input: $0.6 Output: $3.6 | Model: 0.300 Completion: 6.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image Out: text | Open Weights Released: 2026-02-01 |
| Qwen3-235B-A22B-Thinking-2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262.1K | 131.1K | Input: $0.3 Output: $3 | Model: 0.150 Completion: 10.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen3-Coder-Next | Qwen/Qwen3-Coder-Next | 262.1K | 65.5K | Input: $0.2 Output: $1.5 | Model: 0.100 Completion: 7.500 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-02-03 |
| Qwen3-Coder-480B-A35B-Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct | 262.1K | 66.5K | Input: $2 Output: $2 | Model: 1.000 Completion: 1.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen 3 Embedding 4B | Qwen/Qwen3-Embedding-4B | 32K | 2K | Input: $0.01 Output: $0 | Model: 0.005 | - | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Qwen 3 Embedding 8B | Qwen/Qwen3-Embedding-8B | 32K | 4.1K | Input: $0.01 Output: $0 | Model: 0.005 | - | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Qwen3-Next-80B-A3B-Thinking | Qwen/Qwen3-Next-80B-A3B-Thinking | 262.1K | 131.1K | Input: $0.3 Output: $2 | Model: 0.150 Completion: 6.667 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-11 |
iFlow¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Kimi-K2 | kimi-k2 | 128K | 64K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12-01 |
| Qwen3-Max-Preview | qwen3-max-preview | 256K | 32K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2025-01-01 |
| DeepSeek-V3 | deepseek-v3 | 128K | 32K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-12-26 |
| Kimi-K2-0905 | kimi-k2-0905 | 256K | 64K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2025-09-05 |
| Qwen3-235B-A22B-Instruct | qwen3-235b-a22b-instruct | 256K | 64K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-01 |
| GLM-4.6 | glm-4.6 | 200K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12-01 Updated: 2025-11-13 |
| DeepSeek-R1 | deepseek-r1 | 128K | 32K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-20 |
| Qwen3-32B | qwen3-32b | 128K | 32K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-12-01 |
| DeepSeek-V3.2-Exp | deepseek-v3.2 | 128K | 64K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Qwen3-235B-A22B | qwen3-235b | 128K | 32K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-12-01 |
| Qwen3-VL-Plus | qwen3-vl-plus | 256K | 32K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-12 | In: text, image Out: text | Released: 2025-01-01 |
| Qwen3-235B-A22B-Thinking | qwen3-235b-a22b-thinking-2507 | 256K | 64K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-01 |
| Qwen3-Max | qwen3-max | 256K | 32K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2025-01-01 |
| Qwen3-Coder-Plus | qwen3-coder-plus | 256K | 64K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-01 |
Inception¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Mercury | mercury | 128K | 16.4K | Input: $0.25 Output: $1 Cache Read: $0.25 Cache Write: $1 | Model: 0.125 Completion: 4.000 Cache: 1.000 | 🔧 🌡️ | 2023-10 | In: text Out: text | Released: 2025-06-26 Updated: 2025-07-31 |
| Mercury Coder | mercury-coder | 128K | 16.4K | Input: $0.25 Output: $1 Cache Read: $0.25 Cache Write: $1 | Model: 0.125 Completion: 4.000 Cache: 1.000 | 🔧 🌡️ | 2023-10 | In: text Out: text | Released: 2025-02-26 Updated: 2025-07-31 |
Inference¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Mistral Nemo 12B Instruct | mistral/mistral-nemo-12b-instruct | 16K | 4.1K | Input: $0.038 Output: $0.1 | Model: 0.019 Completion: 2.632 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Google Gemma 3 | google/gemma-3 | 125K | 4.1K | Input: $0.15 Output: $0.3 | Model: 0.075 Completion: 2.000 | 📎 🔧 🌡️ | 2024-12 | In: text, image Out: text | Open Weights Released: 2025-01-01 |
| Qwen 3 Embedding 4B | qwen/qwen3-embedding-4b | 32K | 2K | Input: $0.01 Output: $0 | Model: 0.005 | - | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Qwen 2.5 7B Vision Instruct | qwen/qwen-2.5-7b-vision-instruct | 125K | 4.1K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 📎 🔧 🌡️ | 2024-12 | In: text, image Out: text | Open Weights Released: 2025-01-01 |
| Llama 3.2 11B Vision Instruct | meta/llama-3.2-11b-vision-instruct | 16K | 4.1K | Input: $0.055 Output: $0.055 | Model: 0.028 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2025-01-01 |
| Llama 3.2 3B Instruct | meta/llama-3.2-3b-instruct | 16K | 4.1K | Input: $0.02 Output: $0.02 | Model: 0.010 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Llama 3.2 1B Instruct | meta/llama-3.2-1b-instruct | 16K | 4.1K | Input: $0.01 Output: $0.01 | Model: 0.005 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Llama 3.1 8B Instruct | meta/llama-3.1-8b-instruct | 16K | 4.1K | Input: $0.025 Output: $0.025 | Model: 0.013 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Osmosis Structure 0.6B | osmosis/osmosis-structure-0.6b | 4K | 2K | Input: $0.1 Output: $0.5 | Model: 0.050 Completion: 5.000 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
IO.NET¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 4.6 | zai-org/GLM-4.6 | 200K | 4.1K | Input: $0.4 Output: $1.75 Cache Read: $0.2 Cache Write: $0.8 | Model: 0.200 Completion: 4.375 Cache: 0.500 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-11-15 |
| DeepSeek R1 | deepseek-ai/DeepSeek-R1-0528 | 128K | 4.1K | Input: $2 Output: $8.75 Cache Read: $1 Cache Write: $4 | Model: 1.000 Completion: 4.375 Cache: 0.500 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-01-20 Updated: 2025-05-28 |
| Qwen 3 Coder 480B | Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar | 106K | 4.1K | Input: $0.22 Output: $0.95 Cache Read: $0.11 Cache Write: $0.44 | Model: 0.110 Completion: 4.318 Cache: 0.500 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-15 |
| Kimi K2 Instruct | moonshotai/Kimi-K2-Instruct-0905 | 32.8K | 4.1K | Input: $0.39 Output: $1.9 Cache Read: $0.195 Cache Write: $0.78 | Model: 0.195 Completion: 4.872 Cache: 0.500 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-09-05 |
| Kimi K2 Thinking | moonshotai/Kimi-K2-Thinking | 32.8K | 4.1K | Input: $0.55 Output: $2.25 Cache Read: $0.275 Cache Write: $1.1 | Model: 0.275 Completion: 4.091 Cache: 0.500 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-11-01 |
| Llama 3.2 90B Vision Instruct | meta-llama/Llama-3.2-90B-Vision-Instruct | 16K | 4.1K | Input: $0.35 Output: $0.4 Cache Read: $0.175 Cache Write: $0.7 | Model: 0.175 Completion: 1.143 Cache: 0.500 | 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Llama 3.3 70B Instruct | meta-llama/Llama-3.3-70B-Instruct | 128K | 4.1K | Input: $0.13 Output: $0.38 Cache Read: $0.065 Cache Write: $0.26 | Model: 0.065 Completion: 2.923 Cache: 0.500 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Llama 4 Maverick 17B 128E Instruct | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 430K | 4.1K | Input: $0.15 Output: $0.6 Cache Read: $0.075 Cache Write: $0.3 | Model: 0.075 Completion: 4.000 Cache: 0.500 | 🔧 🌡️ | 2024-12 | In: text, image Out: text | Open Weights Released: 2025-01-15 |
| Qwen 3 Next 80B Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | 262.1K | 4.1K | Input: $0.1 Output: $0.8 Cache Read: $0.05 Cache Write: $0.2 | Model: 0.050 Completion: 8.000 Cache: 0.500 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-10 |
| Qwen 3 235B Thinking | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262.1K | 4.1K | Input: $0.11 Output: $0.6 Cache Read: $0.055 Cache Write: $0.22 | Model: 0.055 Completion: 5.455 Cache: 0.500 | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-07-01 |
| Qwen 2.5 VL 32B Instruct | Qwen/Qwen2.5-VL-32B-Instruct | 32K | 4.1K | Input: $0.05 Output: $0.22 Cache Read: $0.025 Cache Write: $0.1 | Model: 0.025 Completion: 4.400 Cache: 0.500 | 🔧 🌡️ | 2024-09 | In: text, image Out: text | Open Weights Released: 2024-11-01 |
| Mistral Nemo Instruct 2407 | mistralai/Mistral-Nemo-Instruct-2407 | 128K | 4.1K | Input: $0.02 Output: $0.04 Cache Read: $0.01 Cache Write: $0.04 | Model: 0.010 Completion: 2.000 Cache: 0.500 | 🔧 🌡️ | 2024-05 | In: text Out: text | Open Weights Released: 2024-07-01 |
| Magistral Small 2506 | mistralai/Magistral-Small-2506 | 128K | 4.1K | Input: $0.5 Output: $1.5 Cache Read: $0.25 Cache Write: $1 | Model: 0.250 Completion: 3.000 Cache: 0.500 | 🔧 🌡️ | 2025-01 | In: text Out: text | Released: 2025-06-01 |
| Mistral Large Instruct 2411 | mistralai/Mistral-Large-Instruct-2411 | 128K | 4.1K | Input: $2 Output: $6 Cache Read: $1 Cache Write: $4 | Model: 1.000 Completion: 3.000 Cache: 0.500 | 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-11-01 |
| Devstral Small 2505 | mistralai/Devstral-Small-2505 | 128K | 4.1K | Input: $0.05 Output: $0.22 Cache Read: $0.025 Cache Write: $0.1 | Model: 0.025 Completion: 4.400 Cache: 0.500 | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2025-05-01 |
| GPT-OSS 120B | openai/gpt-oss-120b | 131.1K | 4.1K | Input: $0.04 Output: $0.4 Cache Read: $0.02 Cache Write: $0.08 | Model: 0.020 Completion: 10.000 Cache: 0.500 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-12-01 |
| GPT-OSS 20B | openai/gpt-oss-20b | 64K | 4.1K | Input: $0.03 Output: $0.14 Cache Read: $0.015 Cache Write: $0.06 | Model: 0.015 Completion: 4.667 Cache: 0.500 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-12-01 |
Jiekou.AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| gpt-5-codex | gpt-5-codex | 400K | 128K | Input: $1.125 Output: $9 | Model: 0.563 Completion: 8.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gpt-5-pro | gpt-5-pro | 400K | 272K | Input: $13.5 Output: $108 | Model: 6.750 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| claude-opus-4-5-20251101 | claude-opus-4-5-20251101 | 200K | 65.5K | Input: $4.5 Output: $22.5 | Model: 2.250 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| grok-4-fast-reasoning | grok-4-fast-reasoning | 2M | 2M | Input: $0.18 Output: $0.45 | Model: 0.090 Completion: 2.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-2.5-flash-lite-preview-09-2025 | gemini-2.5-flash-lite-preview-09-2025 | 1M | 65.5K | Input: $0.09 Output: $0.36 | Model: 0.045 Completion: 4.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| gpt-5-chat-latest | gpt-5-chat-latest | 400K | 128K | Input: $1.125 Output: $9 | Model: 0.563 Completion: 8.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-2.5-pro-preview-06-05 | gemini-2.5-pro-preview-06-05 | 1M | 200K | Input: $1.125 Output: $9 | Model: 0.563 Completion: 8.000 | 📎 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| gpt-5.1-codex-max | gpt-5.1-codex-max | 400K | 128K | Input: $1.125 Output: $9 | Model: 0.563 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| grok-4-0709 | grok-4-0709 | 256K | 8.2K | Input: $2.7 Output: $13.5 | Model: 1.350 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gpt-5.2-codex | gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 | Model: 0.875 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| claude-opus-4-6 | claude-opus-4-6 | 1M | 128K | Input: $5 Output: $25 | Model: 2.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-02 |
| grok-code-fast-1 | grok-code-fast-1 | 256K | 256K | Input: $0.18 Output: $1.35 | Model: 0.090 Completion: 7.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-2.5-flash-preview-05-20 | gemini-2.5-flash-preview-05-20 | 1M | 200K | Input: $0.135 Output: $3.15 | Model: 0.068 Completion: 23.333 | 📎 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| grok-4-1-fast-reasoning | grok-4-1-fast-reasoning | 2M | 2M | Input: $0.18 Output: $0.45 | Model: 0.090 Completion: 2.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-2.5-flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.27 Output: $2.25 | Model: 0.135 Completion: 8.333 | 📎 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| grok-4-1-fast-non-reasoning | grok-4-1-fast-non-reasoning | 2M | 2M | Input: $0.18 Output: $0.45 | Model: 0.090 Completion: 2.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gpt-5.1 | gpt-5.1 | 400K | 128K | Input: $1.125 Output: $9 | Model: 0.563 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-02 |
| o3 | o3 | 131.1K | 131.1K | Input: $10 Output: $40 | Model: 5.000 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-3-flash-preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 | Model: 0.250 Completion: 6.000 | 📎 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| claude-opus-4-20250514 | claude-opus-4-20250514 | 200K | 32K | Input: $13.5 Output: $67.5 | Model: 6.750 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| claude-sonnet-4-5-20250929 | claude-sonnet-4-5-20250929 | 200K | 64K | Input: $2.7 Output: $13.5 | Model: 1.350 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-2.5-flash-lite | gemini-2.5-flash-lite | 1M | 65.5K | Input: $0.09 Output: $0.36 | Model: 0.045 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| gpt-5.1-codex-mini | gpt-5.1-codex-mini | 400K | 128K | Input: $0.225 Output: $1.8 | Model: 0.113 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gpt-5.2 | gpt-5.2 | 400K | 128K | Input: $1.575 Output: $12.6 | Model: 0.787 Completion: 8.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| claude-haiku-4-5-20251001 | claude-haiku-4-5-20251001 | 20K | 64K | Input: $0.9 Output: $4.5 | Model: 0.450 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| o4-mini | o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 | Model: 0.550 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-2.5-flash-lite-preview-06-17 | gemini-2.5-flash-lite-preview-06-17 | 1M | 65.5K | Input: $0.09 Output: $0.36 | Model: 0.045 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, video, image, audio Out: text | Released: 2026-01 |
| gpt-5.1-codex | gpt-5.1-codex | 400K | 128K | Input: $1.125 Output: $9 | Model: 0.563 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gpt-5.2-pro | gpt-5.2-pro | 400K | 128K | Input: $18.9 Output: $151.2 | Model: 9.450 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-3-pro-preview | gemini-3-pro-preview | 1M | 65.5K | Input: $1.8 Output: $10.8 | Model: 0.900 Completion: 6.000 | 📎 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| o3-mini | o3-mini | 131.1K | 131.1K | Input: $1.1 Output: $4.4 | Model: 0.550 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| grok-4-fast-non-reasoning | grok-4-fast-non-reasoning | 2M | 2M | Input: $0.18 Output: $0.45 | Model: 0.090 Completion: 2.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gpt-5-mini | gpt-5-mini | 400K | 128K | Input: $0.225 Output: $1.8 | Model: 0.113 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| claude-sonnet-4-20250514 | claude-sonnet-4-20250514 | 200K | 64K | Input: $2.7 Output: $13.5 | Model: 1.350 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| claude-opus-4-1-20250805 | claude-opus-4-1-20250805 | 200K | 32K | Input: $13.5 Output: $67.5 | Model: 6.750 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| gemini-2.5-pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.125 Output: $9 | Model: 0.563 Completion: 8.000 | 📎 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2026-01 |
| gpt-5-nano | gpt-5-nano | 400K | 128K | Input: $0.045 Output: $0.36 | Model: 0.022 Completion: 8.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01 |
| GLM-4.5 | zai-org/glm-4.5 | 131.1K | 98.3K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| GLM-4.7-Flash | zai-org/glm-4.7-flash | 200K | 128K | Input: $0.07 Output: $0.4 | Model: 0.035 Completion: 5.714 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| GLM-4.7 | zai-org/glm-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| GLM 4.5V | zai-org/glm-4.5v | 65.5K | 16.4K | Input: $0.6 Output: $1.8 | Model: 0.300 Completion: 3.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2026-01 |
| MiniMax M1 | minimaxai/minimax-m1-80k | 1M | 40K | Input: $0.55 Output: $2.2 | Model: 0.275 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| DeepSeek V3.1 | deepseek/deepseek-v3.1 | 163.8K | 32.8K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| DeepSeek R1 0528 | deepseek/deepseek-r1-0528 | 163.8K | 32.8K | Input: $0.7 Output: $2.5 | Model: 0.350 Completion: 3.571 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| DeepSeek V3 0324 | deepseek/deepseek-v3-0324 | 163.8K | 163.8K | Input: $0.28 Output: $1.14 | Model: 0.140 Completion: 4.071 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Kimi K2 Instruct | moonshotai/kimi-k2-instruct | 131.1K | 131.1K | Input: $0.57 Output: $2.3 | Model: 0.285 Completion: 4.035 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Kimi K2 0905 | moonshotai/kimi-k2-0905 | 262.1K | 262.1K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Kimi K2.5 | moonshotai/kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 | Model: 0.300 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2026-01 |
| ERNIE 4.5 VL 424B A47B | baidu/ernie-4.5-vl-424b-a47b | 123K | 16K | Input: $0.42 Output: $1.25 | Model: 0.210 Completion: 2.976 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-01 |
| ERNIE 4.5 300B A47B | baidu/ernie-4.5-300b-a47b-paddle | 123K | 12K | Input: $0.28 Output: $1.1 | Model: 0.140 Completion: 3.929 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Qwen3 235B A22B Instruct 2507 | qwen/qwen3-235b-a22b-instruct-2507 | 131.1K | 16.4K | Input: $0.15 Output: $0.8 | Model: 0.075 Completion: 5.333 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Qwen3 32B | qwen/qwen3-32b-fp8 | 41K | 20K | Input: $0.1 Output: $0.45 | Model: 0.050 Completion: 4.500 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Qwen3 Next 80B A3B Thinking | qwen/qwen3-next-80b-a3b-thinking | 65.5K | 65.5K | Input: $0.15 Output: $1.5 | Model: 0.075 Completion: 10.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Qwen3 Coder 480B A35B Instruct | qwen/qwen3-coder-480b-a35b-instruct | 262.1K | 65.5K | Input: $0.29 Output: $1.2 | Model: 0.145 Completion: 4.138 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Qwen3 30B A3B | qwen/qwen3-30b-a3b-fp8 | 41K | 20K | Input: $0.09 Output: $0.45 | Model: 0.045 Completion: 5.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| qwen/qwen3-coder-next | qwen/qwen3-coder-next | 262.1K | 65.5K | Input: $0.2 Output: $1.5 | Model: 0.100 Completion: 7.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02 |
| Qwen3 235B A22b Thinking 2507 | qwen/qwen3-235b-a22b-thinking-2507 | 131.1K | 131.1K | Input: $0.3 Output: $3 | Model: 0.150 Completion: 10.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Qwen3 Next 80B A3B Instruct | qwen/qwen3-next-80b-a3b-instruct | 65.5K | 65.5K | Input: $0.15 Output: $1.5 | Model: 0.075 Completion: 10.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Qwen3 235B A22B | qwen/qwen3-235b-a22b-fp8 | 41K | 20K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| Minimax M2.1 | minimax/minimax-m2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
| XiaomiMiMo/MiMo-V2-Flash | xiaomimimo/mimo-v2-flash | 262.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01 |
Kilo Gateway¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Prime Intellect: INTELLECT-3 | prime-intellect/intellect-3 | 131.1K | 131.1K | Input: $0.2 Output: $1.1 | Model: 0.100 Completion: 5.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-11-26 Updated: 2026-02-04 |
| AllenAI: Molmo2 8B | allenai/molmo-2-8b | 36.9K | 36.9K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 📎 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2026-01-09 Updated: 2026-01-31 |
| Nex AGI: DeepSeek V3.1 Nex N1 | nex-agi/deepseek-v3.1-nex-n1 | 131.1K | 163.8K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 Updated: 2025-11-25 |
| NVIDIA: Llama 3.1 Nemotron 70B Instruct | nvidia/llama-3.1-nemotron-70b-instruct | 131.1K | 16.4K | Input: $1.2 Output: $1.2 | Model: 0.600 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-10-12 |
| NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 | nvidia/llama-3.1-nemotron-ultra-253b-v1 | 131.1K | 26.2K | Input: $0.6 Output: $1.8 | Model: 0.300 Completion: 3.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-01 Updated: 2026-02-04 |
| NVIDIA: Nemotron Nano 9B V2 (free) | nvidia/nemotron-nano-9b-v2:free | 128K | 25.6K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-05 Updated: 2025-08-18 |
| NVIDIA: Nemotron Nano 12B 2 VL (free) | nvidia/nemotron-nano-12b-v2-vl:free | 128K | 128K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | - | In: image, text, video Out: text | Open Weights Released: 2025-10-28 Updated: 2026-01-31 |
| NVIDIA: Nemotron 3 Nano 30B A3B (free) | nvidia/nemotron-3-nano-30b-a3b:free | 256K | 51.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-14 Updated: 2026-01-31 |
| NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 | nvidia/llama-3.3-nemotron-super-49b-v1.5 | 131.1K | 26.2K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-03-16 |
| NVIDIA: Nemotron Nano 12B 2 VL | nvidia/nemotron-nano-12b-v2-vl | 131.1K | 26.2K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 📎 🧠 🌡️ | - | In: image, text, video Out: text | Open Weights Released: 2025-10-28 Updated: 2026-01-31 |
| NVIDIA: Nemotron Nano 9B V2 | nvidia/nemotron-nano-9b-v2 | 131.1K | 26.2K | Input: $0.04 Output: $0.16 | Model: 0.020 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-18 |
| NVIDIA: Nemotron 3 Nano 30B A3B | nvidia/nemotron-3-nano-30b-a3b | 262.1K | 52.4K | Input: $0.05 Output: $0.2 | Model: 0.025 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12 Updated: 2026-02-04 |
| Arcee AI: Trinity Mini | arcee-ai/trinity-mini | 131.1K | 131.1K | Input: $0.045 Output: $0.15 | Model: 0.022 Completion: 3.333 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12 Updated: 2026-01-28 |
| Arcee AI: Trinity Large Preview (free) | arcee-ai/trinity-large-preview:free | 131K | 26.2K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-28 |
| Arcee AI: Trinity Mini (free) | arcee-ai/trinity-mini:free | 131.1K | 26.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-28 |
| Xiaomi: MiMo-V2-Flash | xiaomi/mimo-v2-flash | 262.1K | 52.4K | Input: $0.09 Output: $0.29 Cache Read: $0.045 | Model: 0.045 Completion: 3.222 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-14 |
| Microsoft: Phi 4 | microsoft/phi-4 | 16.4K | 16.4K | Input: $0.06 Output: $0.14 | Model: 0.030 Completion: 2.333 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-11 |
| WizardLM-2 8x22B | microsoft/wizardlm-2-8x22b | 65.5K | 8K | Input: $0.62 Output: $0.62 | Model: 0.310 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-24 |
| LiquidAI: LFM2.5-1.2B-Thinking (free) | liquid/lfm-2.5-1.2b-thinking:free | 32.8K | 6.6K | Input: $0 Output: $0 | - | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-20 Updated: 2026-01-28 |
| LiquidAI: LFM2.5-1.2B-Instruct (free) | liquid/lfm-2.5-1.2b-instruct:free | 32.8K | 6.6K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-20 Updated: 2026-01-28 |
| Inception: Mercury | inception/mercury | 128K | 16.4K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-06-26 Updated: 2025-07-31 |
| Inception: Mercury Coder | inception/mercury-coder | 128K | 16.4K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-02-26 Updated: 2025-07-31 |
| Amazon: Nova 2 Lite | amazon/nova-2-lite-v1 | 1M | 65.5K | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2024-12-01 Updated: 2025-12-01 |
| Amazon: Nova Pro 1.0 | amazon/nova-pro-v1 | 300K | 5.1K | Input: $0.8 Output: $3.2 | Model: 0.400 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-12-03 |
| EssentialAI: Rnj 1 Instruct | essentialai/rnj-1-instruct | 32.8K | 6.6K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-05 |
| MythoMax 13B | gryphe/mythomax-l2-13b | 4.1K | 4.1K | Input: $0.06 Output: $0.06 | Model: 0.030 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-25 |
| StepFun: Step 3.5 Flash (free) | stepfun/step-3.5-flash:free | 256K | 256K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-29 |
| StepFun: Step 3.5 Flash | stepfun/step-3.5-flash | 256K | 256K | Input: $0.1 Output: $0.3 Cache Read: $0.02 | Model: 0.050 Completion: 3.000 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-29 |
| Venice: Uncensored (free) | cognitivecomputations/dolphin-mistral-24b-venice-edition:free | 32.8K | 6.6K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-09 Updated: 2026-01-31 |
| Tencent: Hunyuan A13B Instruct | tencent/hunyuan-a13b-instruct | 131.1K | 131.1K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🧠 🌡️ | - | In: text Out: text | Released: 2025-06-30 Updated: 2025-11-25 |
| Kwaipilot: KAT-Coder-Pro V1 | kwaipilot/kat-coder-pro | 256K | 128K | Input: $0.207 Output: $0.828 Cache Read: $0.0414 | Model: 0.103 Completion: 4.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-30 Updated: 2025-10-24 |
| DeepSeek: DeepSeek V3.1 Terminus (exacto) | deepseek/deepseek-v3.1-terminus:exacto | 163.8K | 32.8K | Input: $0.21 Output: $0.79 Cache Read: $0.168 | Model: 0.105 Completion: 3.762 Cache: 0.800 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-22 |
| DeepSeek: R1 0528 (free) | deepseek/deepseek-r1-0528:free | 163.8K | 163.8K | Input: $0 Output: $0 | - | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek: R1 0528 | deepseek/deepseek-r1-0528 | 163.8K | 65.5K | Input: $0.4 Output: $1.75 Cache Read: $0.2 | Model: 0.200 Completion: 4.375 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek: R1 | deepseek/deepseek-r1 | 64K | 16K | Input: $0.7 Output: $2.5 | Model: 0.350 Completion: 3.571 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-20 |
| DeepSeek: DeepSeek V3.2 Speciale | deepseek/deepseek-v3.2-speciale | 163.8K | 65.5K | Input: $0.27 Output: $0.41 Cache Read: $0.135 | Model: 0.135 Completion: 1.519 Cache: 0.500 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-01 |
| DeepSeek: DeepSeek V3.1 | deepseek/deepseek-chat-v3.1 | 32.8K | 7.2K | Input: $0.15 Output: $0.75 | Model: 0.075 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-21 |
| DeepSeek: DeepSeek V3 0324 | deepseek/deepseek-chat-v3-0324 | 163.8K | 65.5K | Input: $0.19 Output: $0.87 Cache Read: $0.095 | Model: 0.095 Completion: 4.579 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-24 |
| DeepSeek: R1 Distill Llama 70B | deepseek/deepseek-r1-distill-llama-70b | 131.1K | 131.1K | Input: $0.03 Output: $0.11 Cache Read: $0.015 | Model: 0.015 Completion: 3.667 Cache: 0.500 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-23 |
| DeepSeek: DeepSeek V3.1 Terminus | deepseek/deepseek-v3.1-terminus | 163.8K | 32.8K | Input: $0.21 Output: $0.79 Cache Read: $0.13 | Model: 0.105 Completion: 3.762 Cache: 0.619 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-22 |
| DeepSeek: DeepSeek V3.2 | deepseek/deepseek-v3.2 | 163.8K | 65.5K | Input: $0.25 Output: $0.38 Cache Read: $0.125 | Model: 0.125 Completion: 1.520 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-01 |
| DeepSeek: DeepSeek V3 | deepseek/deepseek-chat | 163.8K | 163.8K | Input: $0.3 Output: $1.2 Cache Read: $0.15 | Model: 0.150 Completion: 4.000 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-01 Updated: 2026-01-10 |
| DeepSeek: R1 Distill Qwen 32B | deepseek/deepseek-r1-distill-qwen-32b | 32.8K | 32.8K | Input: $0.29 Output: $0.29 | Model: 0.145 Completion: 1.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-01 Updated: 2025-11-25 |
| DeepSeek: DeepSeek V3.2 Exp | deepseek/deepseek-v3.2-exp | 163.8K | 65.5K | Input: $0.27 Output: $0.41 | Model: 0.135 Completion: 1.519 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-01 Updated: 2025-09-29 |
| Aurora Alpha (free) | openrouter/aurora-alpha | 128K | 50K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-09 |
| MoonshotAI: Kimi K2 0711 | moonshotai/kimi-k2 | 131.1K | 26.2K | Input: $0.5 Output: $2.4 | Model: 0.250 Completion: 4.800 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-11 |
| MoonshotAI: Kimi K2 0905 | moonshotai/kimi-k2-0905 | 131.1K | 26.2K | Input: $0.4 Output: $2 Cache Read: $0.15 | Model: 0.200 Completion: 5.000 Cache: 0.375 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-05 |
| MoonshotAI: Kimi K2 0905 (exacto) | moonshotai/kimi-k2-0905:exacto | 262.1K | 52.4K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-05 |
| MoonshotAI: Kimi K2.5 | moonshotai/kimi-k2.5 | 262.1K | 262.1K | Input: $0.23 Output: $3 | Model: 0.115 Completion: 13.043 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-01-27 |
| MoonshotAI: Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 262.1K | 65.5K | Input: $0.4 Output: $1.75 Cache Read: $0.2 | Model: 0.200 Completion: 4.375 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-11-06 |
| **Baidu: ERNIE 4.5 VL 424B A47B ** | baidu/ernie-4.5-vl-424b-a47b | 123K | 16K | Input: $0.42 Output: $1.25 | Model: 0.210 Completion: 2.976 | 📎 🧠 🌡️ | - | In: image, text Out: text | Open Weights Released: 2025-06-30 Updated: 2026-01 |
| Baidu: ERNIE 4.5 VL 28B A3B | baidu/ernie-4.5-vl-28b-a3b | 30K | 8K | Input: $0.14 Output: $0.56 | Model: 0.070 Completion: 4.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-06-30 |
| Baidu: ERNIE 4.5 21B A3B Thinking | baidu/ernie-4.5-21b-a3b-thinking | 131.1K | 65.5K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-19 |
| **Baidu: ERNIE 4.5 300B A47B ** | baidu/ernie-4.5-300b-a47b | 123K | 12K | Input: $0.28 Output: $1.1 | Model: 0.140 Completion: 3.929 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-30 Updated: 2026-01 |
| Baidu: ERNIE 4.5 21B A3B | baidu/ernie-4.5-21b-a3b | 120K | 8K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-30 |
| Google: Gemini 2.5 Flash Lite Preview 09-2025 | google/gemini-2.5-flash-lite-preview-09-2025 | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.01 Cache Write: $0.083333 | Model: 0.050 Completion: 4.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-09-25 |
| Google: Gemma 3n 4B (free) | google/gemma-3n-e4b-it:free | 8.2K | 2K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-05-20 |
| Google: Gemini 2.5 Flash Preview 09-2025 | google/gemini-2.5-flash-preview-09-2025 | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.03 Cache Write: $0.083333 | Model: 0.150 Completion: 8.333 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text, audio, video Out: text | Released: 2025-09-25 |
| Google: Gemini 2.5 Pro Preview 05-06 | google/gemini-2.5-pro-preview-05-06 | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.125 Cache Write: $0.375 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-05-06 |
| Google: Gemma 3n 2B (free) | google/gemma-3n-e2b-it:free | 8.2K | 2K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-09 |
| Google: Gemini 2.5 Flash | google/gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.03 Cache Write: $0.083333 | Model: 0.150 Completion: 8.333 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text, audio, video Out: text | Released: 2025-07-17 |
| Google: Gemini 2.5 Pro Preview 06-05 | google/gemini-2.5-pro-preview | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.125 Cache Write: $0.375 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text, audio Out: text | Released: 2025-06-05 Updated: 2026-01 |
| Google: Gemini 2.0 Flash | google/gemini-2.0-flash-001 | 1M | 8.2K | Input: $0.1 Output: $0.4 Cache Read: $0.025 Cache Write: $0.083333 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2024-12-11 |
| Google: Gemini 3 Flash Preview | google/gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 Cache Write: $0.083333 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-12-17 |
| Google: Gemma 3 12B (free) | google/gemma-3-12b-it:free | 32.8K | 8.2K | Input: $0 Output: $0 | - | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Google: Gemma 2 27B | google/gemma-2-27b-it | 8.2K | 2K | Input: $0.65 Output: $0.65 | Model: 0.325 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-06-24 |
| Google: Gemini 2.5 Flash Lite | google/gemini-2.5-flash-lite | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.01 Cache Write: $0.083333 | Model: 0.050 Completion: 4.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-06-17 |
| Google: Gemini 2.0 Flash Lite | google/gemini-2.0-flash-lite-001 | 1M | 8.2K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2024-12-11 Updated: 2025-06-16 |
| Google: Gemma 2 9B | google/gemma-2-9b-it | 8.2K | 1.6K | Input: $0.03 Output: $0.09 | Model: 0.015 Completion: 3.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-06-28 |
| Google: Gemma 3 4B (free) | google/gemma-3-4b-it:free | 32.8K | 8.2K | Input: $0 Output: $0 | - | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Google: Gemma 3n 4B | google/gemma-3n-e4b-it | 32.8K | 6.6K | Input: $0.02 Output: $0.04 | Model: 0.010 Completion: 2.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-05-20 |
| Google: Gemini 3 Pro Preview | google/gemini-3-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 Cache Write: $0.375 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-11-18 Updated: 2025-11 |
| Google: Gemma 3 12B | google/gemma-3-12b-it | 131.1K | 131.1K | Input: $0.03 Output: $0.1 Cache Read: $0.015 | Model: 0.015 Completion: 3.333 Cache: 0.500 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Google: Gemma 3 4B | google/gemma-3-4b-it | 96K | 19.2K | Input: $0.01703 Output: $0.068154 | Model: 0.009 Completion: 4.002 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Google: Gemma 3 27B | google/gemma-3-27b-it | 128K | 65.5K | Input: $0.04 Output: $0.15 Cache Read: $0.02 | Model: 0.020 Completion: 3.750 Cache: 0.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-12 |
| Google: Gemini 2.5 Pro | google/gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.125 Cache Write: $0.375 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| Google: Gemma 3 27B (free) | google/gemma-3-27b-it:free | 131.1K | 8.2K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-12 |
| Z.ai: GLM 5 | z-ai/glm-5 | 204.8K | 131.1K | Input: $0.3 Output: $2.55 | Model: 0.150 Completion: 8.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| Z.ai: GLM 4.5 Air | z-ai/glm-4.5-air | 131.1K | 98.3K | Input: $0.13 Output: $0.85 Cache Read: $0.025 | Model: 0.065 Completion: 6.538 Cache: 0.192 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-28 |
| Z.ai: GLM 4.5 | z-ai/glm-4.5 | 131.1K | 65.5K | Input: $0.35 Output: $1.55 Cache Read: $0.175 | Model: 0.175 Completion: 4.429 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-28 |
| Z.ai: GLM 4.6 (exacto) | z-ai/glm-4.6:exacto | 204.8K | 131.1K | Input: $0.44 Output: $1.76 Cache Read: $0.11 | Model: 0.220 Completion: 4.000 Cache: 0.250 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-30 |
| Z.ai: GLM 4.7 Flash | z-ai/glm-4.7-flash | 202.8K | 40.6K | Input: $0.06 Output: $0.4 Cache Read: $0.01 | Model: 0.030 Completion: 6.667 Cache: 0.167 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-19 |
| Z.ai: GLM 4.5 Air (free) | z-ai/glm-4.5-air:free | 131.1K | 96K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-28 |
| Z.ai: GLM 4.6 | z-ai/glm-4.6 | 202.8K | 65.5K | Input: $0.35 Output: $1.5 Cache Read: $0.175 | Model: 0.175 Completion: 4.286 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-30 |
| Z.ai: GLM 5 (free) | z-ai/glm-5:free | 202.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| Z.ai: GLM 4.7 | z-ai/glm-4.7 | 202.8K | 65.5K | Input: $0.4 Output: $1.5 Cache Read: $0.2 | Model: 0.200 Completion: 3.750 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-22 |
| Z.ai: GLM 4.5V | z-ai/glm-4.5v | 65.5K | 16.4K | Input: $0.6 Output: $1.8 Cache Read: $0.11 | Model: 0.300 Completion: 3.000 Cache: 0.183 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-08-11 |
| Z.ai: GLM 4.6V | z-ai/glm-4.6v | 131.1K | 131.1K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 📎 🧠 🔧 🌡️ | - | In: image, text, video Out: text | Open Weights Released: 2025-09-30 Updated: 2026-01-10 |
| Meituan: LongCat Flash Chat | meituan/longcat-flash-chat | 131.1K | 32.8K | Input: $0.2 Output: $0.8 Cache Read: $0.2 | Model: 0.100 Completion: 4.000 Cache: 1.000 | 🌡️ | - | In: text Out: text | Released: 2025-08-30 |
| Qwen: Qwen VL Plus | qwen/qwen-vl-plus | 131.1K | 8.2K | Input: $0.21 Output: $0.63 Cache Read: $0.042 | Model: 0.105 Completion: 3.000 Cache: 0.200 | 📎 🌡️ | - | In: text, image Out: text | Released: 2024-01-25 Updated: 2025-08-15 |
| Qwen: Qwen VL Max | qwen/qwen-vl-max | 131.1K | 32.8K | Input: $0.8 Output: $3.2 | Model: 0.400 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-04-08 Updated: 2025-08-13 |
| Qwen: Qwen3 Next 80B A3B Thinking | qwen/qwen3-next-80b-a3b-thinking | 128K | 25.6K | Input: $0.15 Output: $1.2 | Model: 0.075 Completion: 8.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen: Qwen2.5-VL 7B Instruct | qwen/qwen-2.5-vl-7b-instruct | 32.8K | 6.6K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2024-08-28 Updated: 2024-09 |
| Qwen: Qwen3 Max Thinking | qwen/qwen3-max-thinking | 262.1K | 65.5K | Input: $1.2 Output: $6 | Model: 0.600 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-01-23 |
| Qwen: Qwen3 14B | qwen/qwen3-14b | 41K | 41K | Input: $0.05 Output: $0.22 Cache Read: $0.025 | Model: 0.025 Completion: 4.400 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04 Updated: 2026-01-10 |
| Qwen: Qwen3 Coder 480B A35B (free) | qwen/qwen3-coder:free | 262K | 262K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen: QwQ 32B | qwen/qwq-32b | 32.8K | 32.8K | Input: $0.15 Output: $0.4 | Model: 0.075 Completion: 2.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-28 Updated: 2025-04-11 |
| Qwen: Qwen3 Coder Flash | qwen/qwen3-coder-flash | 1M | 65.5K | Input: $0.3 Output: $1.5 Cache Read: $0.06 | Model: 0.150 Completion: 5.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-23 |
| Qwen: Qwen3 VL 8B Thinking | qwen/qwen3-vl-8b-thinking | 131.1K | 32.8K | Input: $0.117 Output: $1.365 | Model: 0.059 Completion: 11.667 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-10-15 Updated: 2025-11-25 |
| Qwen: Qwen2.5 VL 32B Instruct | qwen/qwen2.5-vl-32b-instruct | 16.4K | 16.4K | Input: $0.05 Output: $0.22 Cache Read: $0.025 | Model: 0.025 Completion: 4.400 Cache: 0.500 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-24 Updated: 2026-01-10 |
| **Qwen: Qwen-Max ** | qwen/qwen-max | 32.8K | 8.2K | Input: $1.6 Output: $6.4 Cache Read: $0.32 | Model: 0.800 Completion: 4.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-04-03 Updated: 2025-01-25 |
| Qwen: Qwen2.5 Coder 7B Instruct | qwen/qwen2.5-coder-7b-instruct | 32.8K | 6.6K | Input: $0.03 Output: $0.09 | Model: 0.015 Completion: 3.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09-17 Updated: 2024-11 |
| Qwen: Qwen3 Coder Next | qwen/qwen3-coder-next | 262.1K | 65.5K | Input: $0.07 Output: $0.3 Cache Read: $0.035 | Model: 0.035 Completion: 4.286 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-02 Updated: 2026-02-08 |
| Qwen: Qwen-Turbo | qwen/qwen-turbo | 131.1K | 8.2K | Input: $0.05 Output: $0.2 Cache Read: $0.01 | Model: 0.025 Completion: 4.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-11-01 Updated: 2025-07-15 |
| Qwen: Qwen3 Coder 480B A35B | qwen/qwen3-coder | 262.1K | 52.4K | Input: $0.22 Output: $1 Cache Read: $0.022 | Model: 0.110 Completion: 4.545 Cache: 0.100 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen: Qwen3 4B | qwen/qwen3-4b | 131.1K | 8.2K | Input: $0.0715 Output: $0.273 | Model: 0.036 Completion: 3.818 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-29 Updated: 2025-07-23 |
| Qwen: Qwen3 8B | qwen/qwen3-8b | 32K | 8.2K | Input: $0.05 Output: $0.4 Cache Read: $0.05 | Model: 0.025 Completion: 8.000 Cache: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04 |
| Qwen: Qwen3 32B | qwen/qwen3-32b | 41K | 41K | Input: $0.08 Output: $0.24 Cache Read: $0.04 | Model: 0.040 Completion: 3.000 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-01 Updated: 2026-02-04 |
| Qwen: Qwen3 235B A22B Instruct 2507 | qwen/qwen3-235b-a22b-2507 | 262.1K | 52.4K | Input: $0.071 Output: $0.1 | Model: 0.035 Completion: 1.408 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04 Updated: 2026-01 |
| Qwen: Qwen3.5 397B A17B | qwen/qwen3.5-397b-a17b | 256K | 64K | Input: $0.6 Output: $3.6 | Model: 0.300 Completion: 6.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2026-02-15 |
| Qwen: Qwen3 Coder 480B A35B (exacto) | qwen/qwen3-coder:exacto | 262.1K | 65.5K | Input: $0.22 Output: $1.8 Cache Read: $0.022 | Model: 0.110 Completion: 8.182 Cache: 0.100 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen: Qwen2.5 7B Instruct | qwen/qwen-2.5-7b-instruct | 32.8K | 6.6K | Input: $0.04 Output: $0.1 | Model: 0.020 Completion: 2.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09 Updated: 2025-04-16 |
| Qwen2.5 Coder 32B Instruct | qwen/qwen-2.5-coder-32b-instruct | 32.8K | 32.8K | Input: $0.03 Output: $0.11 Cache Read: $0.015 | Model: 0.015 Completion: 3.667 Cache: 0.500 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-11 |
| Qwen: Qwen3.5 Plus 2026-02-15 | qwen/qwen3.5-plus-02-15 | 1M | 64K | Input: $0.4 Output: $2.4 | Model: 0.200 Completion: 6.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2026-02-15 |
| Qwen: Qwen3 30B A3B Instruct 2507 | qwen/qwen3-30b-a3b-instruct-2507 | 262.1K | 262.1K | Input: $0.08 Output: $0.33 Cache Read: $0.04 | Model: 0.040 Completion: 4.125 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-29 |
| Qwen: Qwen2.5 VL 72B Instruct | qwen/qwen2.5-vl-72b-instruct | 32.8K | 32.8K | Input: $0.15 Output: $0.6 Cache Read: $0.075 | Model: 0.075 Completion: 4.000 Cache: 0.500 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-02-01 |
| Qwen: Qwen3 235B A22B | qwen/qwen3-235b-a22b | 41K | 41K | Input: $0.3 Output: $1.2 Cache Read: $0.15 | Model: 0.150 Completion: 4.000 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-01 Updated: 2026-01 |
| Qwen: Qwen3 Coder 30B A3B Instruct | qwen/qwen3-coder-30b-a3b-instruct | 160K | 32.8K | Input: $0.07 Output: $0.27 | Model: 0.035 Completion: 3.857 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-31 |
| Qwen: Qwen3 VL 235B A22B Instruct | qwen/qwen3-vl-235b-a22b-instruct | 262.1K | 52.4K | Input: $0.2 Output: $0.88 Cache Read: $0.11 | Model: 0.100 Completion: 4.400 Cache: 0.550 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-09-23 Updated: 2026-01-10 |
| Qwen2.5 72B Instruct | qwen/qwen-2.5-72b-instruct | 32.8K | 16.4K | Input: $0.12 Output: $0.39 | Model: 0.060 Completion: 3.250 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09 Updated: 2026-01-10 |
| Qwen: Qwen3 VL 30B A3B Thinking | qwen/qwen3-vl-30b-a3b-thinking | 131.1K | 32.8K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-10-11 Updated: 2025-11-25 |
| Qwen: Qwen3 Next 80B A3B Instruct (free) | qwen/qwen3-next-80b-a3b-instruct:free | 262.1K | 52.4K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen: Qwen3 4B (free) | qwen/qwen3-4b:free | 41K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-30 Updated: 2025-07-23 |
| Qwen: Qwen3 VL 235B A22B Thinking | qwen/qwen3-vl-235b-a22b-thinking | 131.1K | 32.8K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-09-24 |
| Qwen: Qwen3 30B A3B Thinking 2507 | qwen/qwen3-30b-a3b-thinking-2507 | 32.8K | 6.6K | Input: $0.051 Output: $0.34 | Model: 0.025 Completion: 6.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-29 |
| Qwen: Qwen-Plus | qwen/qwen-plus | 1M | 32.8K | Input: $0.4 Output: $1.2 Cache Read: $0.08 | Model: 0.200 Completion: 3.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-01-25 Updated: 2025-09-11 |
| Qwen: Qwen3 235B A22B Thinking 2507 | qwen/qwen3-235b-a22b-thinking-2507 | 131.1K | 26.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen: Qwen3 VL 30B A3B Instruct | qwen/qwen3-vl-30b-a3b-instruct | 131.1K | 32.8K | Input: $0.13 Output: $0.52 | Model: 0.065 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-10-05 Updated: 2025-11-25 |
| Qwen: Qwen3 Next 80B A3B Instruct | qwen/qwen3-next-80b-a3b-instruct | 262.1K | 52.4K | Input: $0.09 Output: $1.1 | Model: 0.045 Completion: 12.222 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen: Qwen3 VL 32B Instruct | qwen/qwen3-vl-32b-instruct | 131.1K | 32.8K | Input: $0.104 Output: $0.416 | Model: 0.052 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-21 Updated: 2025-11-25 |
| Qwen: Qwen3 VL 8B Instruct | qwen/qwen3-vl-8b-instruct | 131.1K | 32.8K | Input: $0.08 Output: $0.5 | Model: 0.040 Completion: 6.250 | 📎 🔧 🌡️ | - | In: image, text Out: text | Open Weights Released: 2025-10-15 Updated: 2025-11-25 |
| Qwen: Qwen3 Max | qwen/qwen3-max | 262.1K | 65.5K | Input: $1.2 Output: $6 Cache Read: $0.24 | Model: 0.600 Completion: 5.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-05 |
| Qwen: Qwen3 30B A3B | qwen/qwen3-30b-a3b | 41K | 41K | Input: $0.06 Output: $0.22 Cache Read: $0.03 | Model: 0.030 Completion: 3.667 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04 Updated: 2026-01 |
| Qwen: Qwen3 Coder Plus | qwen/qwen3-coder-plus | 1M | 65.5K | Input: $1 Output: $5 Cache Read: $0.2 | Model: 0.500 Completion: 5.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-01 Updated: 2025-07-23 |
| xAI: Grok 3 | x-ai/grok-3 | 131.1K | 26.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-02-17 |
| xAI: Grok Code Fast 1 | x-ai/grok-code-fast-1 | 256K | 10K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-26 |
| xAI: Grok 4 Fast | x-ai/grok-4-fast | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-19 |
| xAI: Grok 4 | x-ai/grok-4 | 256K | 51.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-07-09 |
| xAI: Grok 4.1 Fast | x-ai/grok-4.1-fast | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-11-19 |
| xAI: Grok 3 Mini Beta | x-ai/grok-3-mini-beta | 131.1K | 26.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-02-17 |
| xAI: Grok 3 Mini | x-ai/grok-3-mini | 131.1K | 26.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-02-17 |
| xAI: Grok 3 Beta | x-ai/grok-3-beta | 131.1K | 26.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-02-17 |
| Meta: Llama 4 Scout | meta-llama/llama-4-scout | 327.7K | 16.4K | Input: $0.08 Output: $0.3 | Model: 0.040 Completion: 3.750 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Meta: Llama 3.1 70B Instruct | meta-llama/llama-3.1-70b-instruct | 131.1K | 26.2K | Input: $0.4 Output: $0.4 | Model: 0.200 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-16 Updated: 2024-07-23 |
| Meta: Llama 3.3 70B Instruct | meta-llama/llama-3.3-70b-instruct | 131.1K | 16.4K | Input: $0.1 Output: $0.32 | Model: 0.050 Completion: 3.200 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-01 Updated: 2026-02-04 |
| Meta: Llama 3.3 70B Instruct (free) | meta-llama/llama-3.3-70b-instruct:free | 128K | 128K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-06 |
| Meta: Llama 3 70B Instruct | meta-llama/llama-3-70b-instruct | 8.2K | 8K | Input: $0.51 Output: $0.74 | Model: 0.255 Completion: 1.451 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-23 |
| Meta: Llama 3.2 11B Vision Instruct | meta-llama/llama-3.2-11b-vision-instruct | 131.1K | 16.4K | Input: $0.049 Output: $0.049 | Model: 0.025 Completion: 1.000 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Meta: Llama 3.2 3B Instruct | meta-llama/llama-3.2-3b-instruct | 131.1K | 16.4K | Input: $0.02 Output: $0.02 | Model: 0.010 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09-18 Updated: 2025-04-03 |
| Meta: Llama 3.2 3B Instruct (free) | meta-llama/llama-3.2-3b-instruct:free | 131.1K | 26.2K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09-25 |
| Llama Guard 3 8B | meta-llama/llama-guard-3-8b | 131.1K | 26.2K | Input: $0.02 Output: $0.06 | Model: 0.010 Completion: 3.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-18 Updated: 2026-02-04 |
| Meta: Llama 3.2 1B Instruct | meta-llama/llama-3.2-1b-instruct | 60K | 12K | Input: $0.027 Output: $0.2 | Model: 0.013 Completion: 7.407 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09-18 Updated: 2026-01-27 |
| Meta: Llama 3.1 405B Instruct | meta-llama/llama-3.1-405b-instruct | 131K | 26.2K | Input: $4 Output: $4 | Model: 2.000 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-16 Updated: 2025-04-05 |
| Meta: Llama 4 Maverick | meta-llama/llama-4-maverick | 1M | 16.4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-04-05 Updated: 2025-12-24 |
| Meta: Llama 3.1 8B Instruct | meta-llama/llama-3.1-8b-instruct | 16.4K | 16.4K | Input: $0.02 Output: $0.05 | Model: 0.010 Completion: 2.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-23 Updated: 2025-12-23 |
| Meta: Llama Guard 4 12B | meta-llama/llama-guard-4-12b | 163.8K | 32.8K | Input: $0.18 Output: $0.18 | Model: 0.090 Completion: 1.000 | 📎 🌡️ | - | In: image, text Out: text | Open Weights Released: 2025-04-05 |
| Meta: Llama 3 8B Instruct | meta-llama/llama-3-8b-instruct | 8.2K | 16.4K | Input: $0.03 Output: $0.04 | Model: 0.015 Completion: 1.333 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-25 Updated: 2025-04-03 |
| TNG: DeepSeek R1T2 Chimera | tngtech/deepseek-r1t2-chimera | 163.8K | 163.8K | Input: $0.25 Output: $0.85 Cache Read: $0.125 | Model: 0.125 Completion: 3.400 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-08 |
| TNG: DeepSeek R1T Chimera | tngtech/deepseek-r1t-chimera | 163.8K | 163.8K | Input: $0.3 Output: $1.2 Cache Read: $0.15 | Model: 0.150 Completion: 4.000 Cache: 0.500 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| TNG: R1T Chimera | tngtech/tng-r1t-chimera | 163.8K | 65.5K | Input: $0.25 Output: $0.85 Cache Read: $0.125 | Model: 0.125 Completion: 3.400 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-11-26 Updated: 2026-01-31 |
| Mistral: Voxtral Small 24B 2507 | mistralai/voxtral-small-24b-2507 | 32K | 6.4K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | - | In: text, audio Out: text | Open Weights Released: 2025-07-01 |
| Mistral: Mistral Medium 3 | mistralai/mistral-medium-3 | 131.1K | 26.2K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-05-07 |
| Mistral: Mistral Small 3 | mistralai/mistral-small-24b-instruct-2501 | 32.8K | 16.4K | Input: $0.05 Output: $0.08 | Model: 0.025 Completion: 1.600 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Mistral: Mistral 7B Instruct v0.3 | mistralai/mistral-7b-instruct-v0.3 | 32.8K | 4.1K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-01 |
| Mistral: Codestral 2508 | mistralai/codestral-2508 | 256K | 51.2K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-01 |
| Mistral: Mistral Small 3.1 24B | mistralai/mistral-small-3.1-24b-instruct | 131.1K | 131.1K | Input: $0.03 Output: $0.11 Cache Read: $0.015 | Model: 0.015 Completion: 3.667 Cache: 0.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-17 |
| Mistral: Mistral Large 3 2512 | mistralai/mistral-large-2512 | 262.1K | 52.4K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2024-11-01 Updated: 2025-12-16 |
| Mistral: Ministral 3 14B 2512 | mistralai/ministral-14b-2512 | 262.1K | 52.4K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-12-16 |
| Mistral: Devstral Medium | mistralai/devstral-medium | 131.1K | 26.2K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-10 |
| Mistral: Mistral Nemo | mistralai/mistral-nemo | 131.1K | 16.4K | Input: $0.02 Output: $0.04 | Model: 0.010 Completion: 2.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-01 Updated: 2024-07-30 |
| Mistral: Devstral 2 2512 | mistralai/devstral-2512 | 262.1K | 65.5K | Input: $0.05 Output: $0.22 Cache Read: $0.025 | Model: 0.025 Completion: 4.400 Cache: 0.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-12 |
| Mistral: Devstral Small 1.1 | mistralai/devstral-small | 131.1K | 26.2K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-05-07 Updated: 2025-07-10 |
| Mistral: Mistral Small 3.2 24B | mistralai/mistral-small-3.2-24b-instruct | 131.1K | 131.1K | Input: $0.06 Output: $0.18 Cache Read: $0.03 | Model: 0.030 Completion: 3.000 Cache: 0.500 | 📎 🔧 🌡️ | - | In: image, text Out: text | Open Weights Released: 2025-06-20 |
| Mistral: Mixtral 8x22B Instruct | mistralai/mixtral-8x22b-instruct | 65.5K | 13.1K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-17 |
| Mistral: Mistral 7B Instruct | mistralai/mistral-7b-instruct | 32.8K | 4.1K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-05-27 |
| Mistral Large 2411 | mistralai/mistral-large-2411 | 131.1K | 26.2K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-24 Updated: 2024-11-04 |
| Mistral: Mistral 7B Instruct v0.1 | mistralai/mistral-7b-instruct-v0.1 | 2.8K | 565 | Input: $0.11 Output: $0.19 | Model: 0.055 Completion: 1.727 | 🌡️ | - | In: text Out: text | Released: 2025-04-03 |
| Mistral Large | mistralai/mistral-large | 128K | 25.6K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-24 Updated: 2025-12-02 |
| Mistral: Mistral Small 3.1 24B (free) | mistralai/mistral-small-3.1-24b-instruct:free | 128K | 25.6K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-17 |
| Mistral: Mistral Medium 3.1 | mistralai/mistral-medium-3.1 | 131.1K | 26.2K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-12 |
| OpenAI: GPT-4o (2024-11-20) | openai/gpt-4o-2024-11-20 | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-11-20 |
| OpenAI: GPT-5 Codex | openai/gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-09-15 |
| OpenAI: GPT-5 Pro | openai/gpt-5-pro | 400K | 128K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | 📎 🧠 🔧 | - | In: image, text Out: text | Released: 2025-10-06 |
| OpenAI: GPT-4o-mini | openai/gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.075 | Model: 0.075 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-07-18 |
| OpenAI: GPT-4o-mini Search Preview | openai/gpt-4o-mini-search-preview | 128K | 16.4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | - | - | In: text Out: text | Released: 2025-01 |
| OpenAI: GPT-4o (extended) | openai/gpt-4o:extended | 128K | 64K | Input: $6 Output: $18 | Model: 3.000 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-05-13 Updated: 2024-08-06 |
| OpenAI: GPT-5.1-Codex-Max | openai/gpt-5.1-codex-max | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-11-13 |
| OpenAI: GPT-4o (2024-05-13) | openai/gpt-4o-2024-05-13 | 128K | 4.1K | Input: $5 Output: $15 | Model: 2.500 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-05-13 |
| OpenAI: GPT-5.2-Codex | openai/gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2026-01-14 |
| OpenAI: gpt-oss-120b (exacto) | openai/gpt-oss-120b:exacto | 131.1K | 26.2K | Input: $0.039 Output: $0.19 | Model: 0.019 Completion: 4.872 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| OpenAI: o3 Deep Research | openai/o3-deep-research | 200K | 100K | Input: $10 Output: $40 Cache Read: $2.5 | Model: 5.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2024-06-26 Updated: 2025-06-27 |
| OpenAI: o1 | openai/o1 | 200K | 100K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | 📎 🔧 | - | In: text, image Out: text | Released: 2024-12-05 Updated: 2025-01-01 |
| OpenAI: GPT-5.1 | openai/gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: image, text Out: text | Released: 2025-11-13 |
| OpenAI: GPT-5.2 Chat | openai/gpt-5.2-chat | 128K | 16.4K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🔧 | - | In: image, text Out: text | Released: 2025-12-11 |
| OpenAI: o4 Mini Deep Research | openai/o4-mini-deep-research | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2024-06-26 Updated: 2025-06-27 |
| OpenAI: GPT-5 Chat | openai/gpt-5-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 | - | In: image, text Out: text | Released: 2025-08-07 |
| OpenAI: GPT-5.1 Chat | openai/gpt-5.1-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🔧 | - | In: image, text Out: text | Released: 2025-11-13 |
| OpenAI: o3 | openai/o3 | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | - | In: image, text Out: text | Released: 2025-04-16 Updated: 2026-01 |
| OpenAI: GPT-4.1 Nano | openai/gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-04-14 Updated: 2025-04-15 |
| OpenAI: GPT-3.5 Turbo (older v0613) | openai/gpt-3.5-turbo-0613 | 4.1K | 4.1K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2023-06-13 |
| OpenAI: GPT-3.5 Turbo | openai/gpt-3.5-turbo | 16.4K | 4.1K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2023-03-01 Updated: 2023-11-06 |
| OpenAI: gpt-oss-120b | openai/gpt-oss-120b | 131.1K | 26.2K | Input: $0.039 Output: $0.19 | Model: 0.019 Completion: 4.872 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| OpenAI: GPT-5.1-Codex-Mini | openai/gpt-5.1-codex-mini | 400K | 100K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: image, text Out: text | Released: 2025-11-13 |
| OpenAI: GPT-5.2 | openai/gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: image, text Out: text | Released: 2025-12-11 |
| OpenAI: gpt-oss-20b (free) | openai/gpt-oss-20b:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 Updated: 2026-01-31 |
| OpenAI: GPT-4.1 | openai/gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-04-14 |
| OpenAI: o3 Pro | openai/o3-pro | 200K | 100K | Input: $20 Output: $80 | Model: 10.000 Completion: 4.000 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-04-16 Updated: 2025-06-10 |
| OpenAI: GPT-4 Turbo | openai/gpt-4-turbo | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2023-09-13 Updated: 2024-04-09 |
| OpenAI: GPT-5 | openai/gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-08-07 |
| OpenAI: o4 Mini | openai/o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.275 | Model: 0.550 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | - | In: image, text Out: text | Released: 2025-04-16 |
| OpenAI: GPT-4.1 Mini | openai/gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-04-14 |
| OpenAI: gpt-oss-safeguard-20b | openai/gpt-oss-safeguard-20b | 131.1K | 65.5K | Input: $0.075 Output: $0.3 Cache Read: $0.037 | Model: 0.037 Completion: 4.000 Cache: 0.493 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-29 |
| OpenAI: o1-pro | openai/o1-pro | 200K | 100K | Input: $150 Output: $600 | Model: 75.000 Completion: 4.000 | 📎 🧠 | - | In: text, image Out: text | Released: 2025-03-19 |
| OpenAI: GPT-5.1-Codex | openai/gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-11-13 |
| OpenAI: ChatGPT-4o | openai/chatgpt-4o-latest | 128K | 16.4K | Input: $5 Output: $15 | Model: 2.500 Completion: 3.000 | 📎 🌡️ | - | In: text, image Out: text | Released: 2024-08-08 Updated: 2024-08-14 |
| OpenAI: GPT-5.2 Pro | openai/gpt-5.2-pro | 400K | 128K | Input: $21 Output: $168 | Model: 10.500 Completion: 8.000 | 📎 🧠 🔧 | - | In: image, text Out: text | Released: 2025-12-11 |
| OpenAI: o3 Mini | openai/o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🔧 | - | In: text Out: text | Released: 2024-12-20 Updated: 2026-01 |
| OpenAI: GPT-4o (2024-08-06) | openai/gpt-4o-2024-08-06 | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-08-06 |
| OpenAI: GPT-5 Mini | openai/gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-08-07 |
| OpenAI: gpt-oss-20b | openai/gpt-oss-20b | 131.1K | 26.2K | Input: $0.03 Output: $0.14 | Model: 0.015 Completion: 4.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| OpenAI: gpt-oss-120b (free) | openai/gpt-oss-120b:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| OpenAI: GPT-4 | openai/gpt-4 | 8.2K | 4.1K | Input: $30 Output: $60 | Model: 15.000 Completion: 2.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2023-03-14 Updated: 2024-04-09 |
| OpenAI: GPT-5 Nano | openai/gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.005 | Model: 0.025 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-08-07 |
| OpenAI: GPT-3.5 Turbo Instruct | openai/gpt-3.5-turbo-instruct | 4.1K | 4.1K | Input: $1.5 Output: $2 | Model: 0.750 Completion: 1.333 | 🌡️ | - | In: text Out: text | Released: 2023-03-01 Updated: 2023-09-21 |
| OpenAI: o3 Mini High | openai/o3-mini-high | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🔧 | - | In: text Out: text | Released: 2025-01-31 |
| OpenAI: GPT-4o | openai/gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-05-13 Updated: 2024-08-06 |
| Morph: Morph V3 Fast | morph/morph-v3-fast | 81.9K | 38K | Input: $0.8 Output: $1.2 | Model: 0.400 Completion: 1.500 | 🌡️ | - | In: text Out: text | Released: 2024-08-15 |
| Morph: Morph V3 Large | morph/morph-v3-large | 262.1K | 131.1K | Input: $0.9 Output: $1.9 | Model: 0.450 Completion: 2.111 | 🌡️ | - | In: text Out: text | Released: 2024-08-15 |
| Cohere: Command R (08-2024) | cohere/command-r-08-2024 | 128K | 4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-30 |
| Cohere: Command R+ (08-2024) | cohere/command-r-plus-08-2024 | 128K | 4K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-30 |
| Cohere: Command R7B (12-2024) | cohere/command-r7b-12-2024 | 128K | 4K | Input: $0.0375 Output: $0.15 | Model: 0.019 Completion: 4.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-02-27 |
| Cohere: Command A | cohere/command-a | 256K | 8.2K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-13 |
| MiniMax: MiniMax M1 | minimax/minimax-m1 | 1M | 40K | Input: $0.4 Output: $2.2 | Model: 0.200 Completion: 5.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-17 |
| MiniMax: MiniMax-01 | minimax/minimax-01 | 1M | 1M | Input: $0.2 Output: $1.1 | Model: 0.100 Completion: 5.500 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-01-15 |
| MiniMax: MiniMax M2.1 | minimax/minimax-m2.1 | 196.6K | 39.3K | Input: $0.27 Output: $0.95 Cache Read: $0.03 | Model: 0.135 Completion: 3.519 Cache: 0.111 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| MiniMax: MiniMax M2.5 (free) | minimax/minimax-m2.5:free | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax: MiniMax M2 | minimax/minimax-m2 | 196.6K | 65.5K | Input: $0.255 Output: $1 Cache Read: $0.03 | Model: 0.128 Completion: 3.922 Cache: 0.118 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-23 |
| MiniMax: MiniMax M2.5 | minimax/minimax-m2.5 | 196.6K | 39.3K | Input: $0.3 Output: $1.2 Cache Read: $0.029 | Model: 0.150 Completion: 4.000 Cache: 0.097 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| Writer: Palmyra X5 | writer/palmyra-x5 | 1M | 8.2K | Input: $0.6 Output: $6 | Model: 0.300 Completion: 10.000 | 🌡️ | - | In: text Out: text | Released: 2025-04-28 |
| Perplexity: Sonar Reasoning Pro | perplexity/sonar-reasoning-pro | 128K | 25.6K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 📎 🧠 🌡️ | - | In: text, image Out: text | Released: 2024-01-01 Updated: 2025-09-01 |
| Perplexity: Sonar | perplexity/sonar | 127.1K | 25.4K | Input: $1 Output: $1 | Model: 0.500 Completion: 1.000 | 📎 🌡️ | - | In: text, image Out: text | Released: 2024-01-01 Updated: 2025-09-01 |
| Perplexity: Sonar Deep Research | perplexity/sonar-deep-research | 128K | 25.6K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 🧠 🌡️ | - | In: text Out: text | Released: 2025-01-27 |
| Perplexity: Sonar Pro | perplexity/sonar-pro | 200K | 8K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🌡️ | - | In: text, image Out: text | Released: 2024-01-01 Updated: 2025-09-01 |
| ByteDance Seed: Seed 1.6 | bytedance-seed/seed-1.6 | 262.1K | 32.8K | Input: $0.25 Output: $2 | Model: 0.125 Completion: 8.000 | 📎 🧠 🔧 🌡️ | - | In: image, text, video Out: text | Released: 2025-09 |
| Anthropic: Claude 3.5 Sonnet | anthropic/claude-3.5-sonnet | 200K | 8.2K | Input: $6 Output: $30 | Model: 3.000 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-10-22 |
| Anthropic: Claude 3.7 Sonnet | anthropic/claude-3.7-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-02-19 |
| Anthropic: Claude Opus 4.1 | anthropic/claude-opus-4.1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-08-05 |
| Anthropic: Claude 3 Haiku | anthropic/claude-3-haiku | 200K | 4.1K | Input: $0.25 Output: $1.25 Cache Read: $0.03 Cache Write: $0.3 | Model: 0.125 Completion: 5.000 Cache: 0.120 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-03-07 |
| Anthropic: Claude Haiku 4.5 | anthropic/claude-haiku-4.5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-10-15 |
| Anthropic: Claude 3.5 Haiku | anthropic/claude-3.5-haiku | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-10-22 |
| Anthropic: Claude 3.7 Sonnet (thinking) | anthropic/claude-3.7-sonnet:thinking | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-02-19 Updated: 2025-02-24 |
| Anthropic: Claude Opus 4.5 | anthropic/claude-opus-4.5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-11-24 |
| Anthropic: Claude Opus 4 | anthropic/claude-opus-4 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-05-22 |
| Anthropic: Claude Sonnet 4 | anthropic/claude-sonnet-4 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: image, text Out: text | Released: 2025-05-22 |
| Anthropic: Claude Sonnet 4.5 | anthropic/claude-sonnet-4.5 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-09-29 |
| Anthropic: Claude Opus 4.6 | anthropic/claude-opus-4.6 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-02-05 |
| Kilo: Auto | kilo/auto | 200K | 64K | Input: $1 Output: $1 | Model: 0.500 Completion: 1.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-06-01 |
| Nous: Hermes 4 405B | nousresearch/hermes-4-405b | 131.1K | 26.2K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-25 |
| Nous: Hermes 4 70B | nousresearch/hermes-4-70b | 131.1K | 131.1K | Input: $0.11 Output: $0.38 Cache Read: $0.055 | Model: 0.055 Completion: 3.455 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-25 |
| Nous: DeepHermes 3 Mistral 24B Preview | nousresearch/deephermes-3-mistral-24b-preview | 32.8K | 32.8K | Input: $0.02 Output: $0.1 Cache Read: $0.01 | Model: 0.010 Completion: 5.000 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-29 Updated: 2026-01-10 |
| Nous: Hermes 3 405B Instruct | nousresearch/hermes-3-llama-3.1-405b | 131.1K | 16.4K | Input: $1 Output: $1 | Model: 0.500 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-16 |
| Nous: Hermes 3 405B Instruct (free) | nousresearch/hermes-3-llama-3.1-405b:free | 131.1K | 26.2K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-16 |
| NousResearch: Hermes 2 Pro - Llama-3 8B | nousresearch/hermes-2-pro-llama-3-8b | 8.2K | 8.2K | Input: $0.14 Output: $0.14 | Model: 0.070 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-05-27 Updated: 2024-06-27 |
Kimi For Coding¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2.5 | k2p5 | 262.1K | 32.8K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01 |
| Kimi K2 Thinking | kimi-k2-thinking | 262.1K | 32.8K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-11 Updated: 2025-12 |
KUAE Cloud Coding Plan¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-4.7 | GLM-4.7 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
Llama¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Cerebras-Llama-4-Maverick-17B-128E-Instruct | cerebras-llama-4-maverick-17b-128e-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-04-05 |
| Llama-4-Scout-17B-16E-Instruct-FP8 | llama-4-scout-17b-16e-instruct-fp8 | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Llama-3.3-8B-Instruct | llama-3.3-8b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Groq-Llama-4-Maverick-17B-128E-Instruct | groq-llama-4-maverick-17b-128e-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-04-05 |
| Llama-3.3-70B-Instruct | llama-3.3-70b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Cerebras-Llama-4-Scout-17B-16E-Instruct | cerebras-llama-4-scout-17b-16e-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-04-05 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | llama-4-maverick-17b-128e-instruct-fp8 | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
LMStudio¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 30B A3B 2507 | qwen/qwen3-30b-a3b-2507 | 262.1K | 16.4K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-30 |
| Qwen3 Coder 30B | qwen/qwen3-coder-30b | 262.1K | 65.5K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| GPT OSS 20B | openai/gpt-oss-20b | 131.1K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
LucidQuery AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| LucidQuery Nexus Coder | lucidquery-nexus-coder | 250K | 60K | Input: $2 Output: $5 | Model: 1.000 Completion: 2.500 | 📎 🧠 🔧 | 2025-08-01 | In: text Out: text | Released: 2025-09-01 |
| LucidNova RF1 100B | lucidnova-rf1-100b | 120K | 8K | Input: $2 Output: $5 | Model: 1.000 Completion: 2.500 | 📎 🧠 🔧 | 2025-09-16 | In: text Out: text | Released: 2024-12-28 Updated: 2025-09-10 |
Meganova¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-4.6 | zai-org/GLM-4.6 | 202.8K | 131.1K | Input: $0.45 Output: $1.9 | Model: 0.225 Completion: 4.222 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7 | zai-org/GLM-4.7 | 202.8K | 131.1K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-5 | zai-org/GLM-5 | 202.8K | 131.1K | Input: $0.8 Output: $2.56 | Model: 0.400 Completion: 3.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-11 |
| MiMo V2 Flash | XiaomiMiMo/MiMo-V2-Flash | 262.1K | 32K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-12-01 | In: text Out: text | Open Weights Released: 2025-12-17 |
| MiniMax M2.5 | MiniMaxAI/MiniMax-M2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax M2.1 | MiniMaxAI/MiniMax-M2.1 | 196.6K | 131.1K | Input: $0.28 Output: $1.2 | Model: 0.140 Completion: 4.286 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| DeepSeek V3.2 Exp | deepseek-ai/DeepSeek-V3.2-Exp | 164K | 164K | Input: $0.27 Output: $0.4 | Model: 0.135 Completion: 1.481 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-10 |
| DeepSeek R1 0528 | deepseek-ai/DeepSeek-R1-0528 | 163.8K | 64K | Input: $0.5 Output: $2.15 | Model: 0.250 Completion: 4.300 | 🧠 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek V3.1 | deepseek-ai/DeepSeek-V3.1 | 164K | 164K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-25 |
| DeepSeek V3.2 | deepseek-ai/DeepSeek-V3.2 | 164K | 164K | Input: $0.26 Output: $0.38 | Model: 0.130 Completion: 1.462 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-03 |
| DeepSeek V3 0324 | deepseek-ai/DeepSeek-V3-0324 | 163.8K | 163.8K | Input: $0.25 Output: $0.88 | Model: 0.125 Completion: 3.520 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-24 |
| Kimi K2.5 | moonshotai/Kimi-K2.5 | 262.1K | 262.1K | Input: $0.45 Output: $2.8 | Model: 0.225 Completion: 6.222 | 🧠 🔧 🌡️ | 2026-01 | In: text, image Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking | moonshotai/Kimi-K2-Thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.6 | Model: 0.300 Completion: 4.333 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Llama 3.3 70B Instruct | meta-llama/Llama-3.3-70B-Instruct | 131.1K | 16.4K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-06 |
| Qwen3.5 Plus | Qwen/Qwen3.5-Plus | 1M | 65.5K | Input: $0.4 Output: $2.4 Reasoning: $2.4 | Model: 0.200 Completion: 6.000 | 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Released: 2026-02 |
| Qwen3 235B A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262K | 262K | Input: $0.09 Output: $0.6 | Model: 0.045 Completion: 6.667 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen2.5 VL 32B Instruct | Qwen/Qwen2.5-VL-32B-Instruct | 16.4K | 16.4K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-24 |
| Mistral Nemo Instruct 2407 | mistralai/Mistral-Nemo-Instruct-2407 | 131.1K | 65.5K | Input: $0.02 Output: $0.04 | Model: 0.010 Completion: 2.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-18 |
| Mistral Small 3.2 24B Instruct | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | 32.8K | 8.2K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-06-20 |
MiniMax (minimax.io)¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| MiniMax-M2.5 | MiniMax-M2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.375 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax-M2 | MiniMax-M2 | 196.6K | 128K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-27 |
| MiniMax-M2.5-highspeed | MiniMax-M2.5-highspeed | 204.8K | 131.1K | Input: $0.6 Output: $2.4 Cache Read: $0.06 Cache Write: $0.375 | Model: 0.300 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-13 |
| MiniMax-M2.1 | MiniMax-M2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
MiniMax (minimaxi.com)¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| MiniMax-M2.5 | MiniMax-M2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.375 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax-M2 | MiniMax-M2 | 196.6K | 128K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-27 |
| MiniMax-M2.5-highspeed | MiniMax-M2.5-highspeed | 204.8K | 131.1K | Input: $0.6 Output: $2.4 Cache Read: $0.06 Cache Write: $0.375 | Model: 0.300 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-13 |
| MiniMax-M2.1 | MiniMax-M2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
MiniMax Coding Plan (minimaxi.com)¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| MiniMax-M2.5 | MiniMax-M2.5 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax-M2 | MiniMax-M2 | 196.6K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-27 |
| MiniMax-M2.5-highspeed | MiniMax-M2.5-highspeed | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-13 |
| MiniMax-M2.1 | MiniMax-M2.1 | 204.8K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
MiniMax Coding Plan (minimax.io)¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| MiniMax-M2.5 | MiniMax-M2.5 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax-M2 | MiniMax-M2 | 196.6K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-27 |
| MiniMax-M2.5-highspeed | MiniMax-M2.5-highspeed | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-13 |
| MiniMax-M2.1 | MiniMax-M2.1 | 204.8K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
Mistral¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Devstral Medium | devstral-medium-2507 | 128K | 128K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-07-10 |
| Devstral Small 2 | labs-devstral-small-2512 | 256K | 256K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-12 | In: text, image Out: text | Open Weights Released: 2025-12-09 |
| Devstral 2 | devstral-medium-latest | 262.1K | 262.1K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-12-02 |
| Mistral 7B | open-mistral-7b | 8K | 8K | Input: $0.25 Output: $0.25 | Model: 0.125 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2023-09-27 |
| Mistral Small 3.2 | mistral-small-2506 | 128K | 16.4K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-03 | In: text, image Out: text | Open Weights Released: 2025-06-20 |
| Mistral Medium 3 | mistral-medium-2505 | 131.1K | 131.1K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-05-07 |
| Codestral | codestral-latest | 256K | 4.1K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-05-29 Updated: 2025-01-04 |
| Ministral 8B | ministral-8b-latest | 128K | 128K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-10-01 Updated: 2024-10-04 |
| Magistral Small | magistral-small | 128K | 128K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-03-17 |
| Mistral Large 3 | mistral-large-2512 | 262.1K | 262.1K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 📎 🔧 🌡️ | 2024-11 | In: text, image Out: text | Open Weights Released: 2024-11-01 Updated: 2025-12-02 |
| Ministral 3B | ministral-3b-latest | 128K | 128K | Input: $0.04 Output: $0.04 | Model: 0.020 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-10-01 Updated: 2024-10-04 |
| Mistral Embed | mistral-embed | 8K | 3.1K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Released: 2023-12-11 |
| Devstral Small 2505 | devstral-small-2505 | 128K | 128K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-07 |
| Pixtral 12B | pixtral-12b | 128K | 128K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 📎 🔧 🌡️ | 2024-09 | In: text, image Out: text | Open Weights Released: 2024-09-01 |
| Mixtral 8x7B | open-mixtral-8x7b | 32K | 32K | Input: $0.7 Output: $0.7 | Model: 0.350 Completion: 1.000 | 🔧 🌡️ | 2024-01 | In: text Out: text | Open Weights Released: 2023-12-11 |
| Pixtral Large | pixtral-large-latest | 128K | 128K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 📎 🔧 🌡️ | 2024-11 | In: text, image Out: text | Open Weights Released: 2024-11-01 Updated: 2024-11-04 |
| Mistral Nemo | mistral-nemo | 128K | 128K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2024-07-01 |
| Devstral 2 | devstral-2512 | 262.1K | 262.1K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-12-09 |
| Mistral Large | mistral-large-latest | 262.1K | 262.1K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 📎 🔧 🌡️ | 2024-11 | In: text, image Out: text | Open Weights Released: 2024-11-01 Updated: 2025-12-02 |
| Mistral Medium 3.1 | mistral-medium-2508 | 262.1K | 262.1K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-08-12 |
| Mistral Large 2.1 | mistral-large-2411 | 131.1K | 16.4K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | 2024-11 | In: text Out: text | Open Weights Released: 2024-11-01 Updated: 2024-11-04 |
| Mistral Small | mistral-small-latest | 128K | 16.4K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-03 | In: text, image Out: text | Open Weights Released: 2024-09-01 Updated: 2024-09-04 |
| Mixtral 8x22B | open-mixtral-8x22b | 64K | 64K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-04-17 |
| Mistral Medium | mistral-medium-latest | 128K | 16.4K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | 2025-05 | In: text, image Out: text | Open Weights Released: 2025-05-07 Updated: 2025-05-10 |
| Devstral Small | devstral-small-2507 | 128K | 128K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-07-10 |
| Magistral Medium | magistral-medium-latest | 128K | 16.4K | Input: $2 Output: $5 | Model: 1.000 Completion: 2.500 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-03-17 Updated: 2025-03-20 |
Moark¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-4.7 | GLM-4.7 | 204.8K | 131.1K | Input: $3.5 Output: $14 | Model: 1.750 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| MiniMax-M2.1 | MiniMax-M2.1 | 204.8K | 131.1K | Input: $2.1 Output: $8.4 | Model: 1.050 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
ModelScope¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3 30B A3B Instruct 2507 | Qwen/Qwen3-30B-A3B-Instruct-2507 | 262.1K | 16.4K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-30 |
| Qwen3-235B-A22B-Thinking-2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen3 30B A3B Thinking 2507 | Qwen/Qwen3-30B-A3B-Thinking-2507 | 262.1K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-30 |
| Qwen3 Coder 30B A3B Instruct | Qwen/Qwen3-Coder-30B-A3B-Instruct | 262.1K | 65.5K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-31 |
| Qwen3 235B A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 Updated: 2025-07-21 |
| GLM-4.6 | ZhipuAI/GLM-4.6 | 202.8K | 98.3K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.5 | ZhipuAI/GLM-4.5 | 131.1K | 98.3K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
Moonshot AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2 0905 | kimi-k2-0905-preview | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2.5 | kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 Cache Read: $0.1 | Model: 0.300 Completion: 5.000 Cache: 0.167 | 🧠 🔧 | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01 |
| Kimi K2 Thinking | kimi-k2-thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Kimi K2 Turbo | kimi-k2-turbo-preview | 262.1K | 262.1K | Input: $2.4 Output: $10 Cache Read: $0.6 | Model: 1.200 Completion: 4.167 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2 Thinking Turbo | kimi-k2-thinking-turbo | 262.1K | 262.1K | Input: $1.15 Output: $8 Cache Read: $0.15 | Model: 0.575 Completion: 6.957 Cache: 0.130 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Kimi K2 0711 | kimi-k2-0711-preview | 131.1K | 16.4K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-14 |
Moonshot AI (China)¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2 0711 | kimi-k2-0711-preview | 131.1K | 16.4K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-14 |
| Kimi K2 Thinking Turbo | kimi-k2-thinking-turbo | 262.1K | 262.1K | Input: $1.15 Output: $8 Cache Read: $0.15 | Model: 0.575 Completion: 6.957 Cache: 0.130 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Kimi K2 Turbo | kimi-k2-turbo-preview | 262.1K | 262.1K | Input: $2.4 Output: $10 Cache Read: $0.6 | Model: 1.200 Completion: 4.167 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2 Thinking | kimi-k2-thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Kimi K2.5 | kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 Cache Read: $0.1 | Model: 0.300 Completion: 5.000 Cache: 0.167 | 🧠 🔧 | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01 |
| Kimi K2 0905 | kimi-k2-0905-preview | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
Morph¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Auto | auto | 32K | 32K | Input: $0.85 Output: $1.55 | Model: 0.425 Completion: 1.824 | - | - | In: text Out: text | Released: 2024-06-01 |
| Morph v3 Fast | morph-v3-fast | 16K | 16K | Input: $0.8 Output: $1.2 | Model: 0.400 Completion: 1.500 | - | - | In: text Out: text | Released: 2024-08-15 |
| Morph v3 Large | morph-v3-large | 32K | 32K | Input: $0.9 Output: $1.9 | Model: 0.450 Completion: 2.111 | - | - | In: text Out: text | Released: 2024-08-15 |
NanoGPT¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 5 Original Thinking | zai-org/glm-5-original:thinking | 200K | 128K | Input: $0.8 Output: $2.56 | Model: 0.400 Completion: 3.200 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-02-11 |
| GLM 5 | zai-org/glm-5 | 200K | 128K | Input: $0.8 Output: $2.56 | Model: 0.400 Completion: 3.200 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-02-11 |
| GLM 5 Original | zai-org/glm-5-original | 200K | 128K | Input: $0.8 Output: $2.56 | Model: 0.400 Completion: 3.200 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-02-11 |
| GLM 4.6 Thinking | zai-org/glm-4.6:thinking | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-07 Updated: 2025-12-24 |
| GLM 4.5 Air | zai-org/glm-4.5-air | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 Updated: 2025-12-24 |
| GLM 4.6 | zai-org/glm-4.6 | 200K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-11-15 Updated: 2025-12-24 |
| GLM 4.7 Thinking | zai-org/glm-4.7:thinking | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-07 Updated: 2025-12-24 |
| GLM 4.7 | zai-org/glm-4.7 | 204.8K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 Updated: 2025-12-24 |
| GLM 4.5 Air Thinking | zai-org/glm-4.5-air:thinking | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-07 Updated: 2025-12-24 |
| GLM 5 Thinking | zai-org/glm-5:thinking | 200K | 128K | Input: $0.8 Output: $2.56 | Model: 0.400 Completion: 3.200 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-02-11 |
| Llama 3 3 Nemotron Super 49B V1 5 | nvidia/llama-3_3-nemotron-super-49b-v1_5 | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-08 Updated: 2025-12-24 |
| Deepseek R1 | deepseek/deepseek-r1 | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-01-20 Updated: 2025-12-24 |
| Deepseek V3.2 Thinking | deepseek/deepseek-v3.2:thinking | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-01 Updated: 2025-12-24 |
| Kimi K2 Instruct | moonshotai/kimi-k2-instruct | 131.1K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-07-18 Updated: 2025-12-24 |
| Kimi K2.5 | moonshotai/kimi-k2.5 | 256K | 65.5K | Input: $0.3 Output: $1.9 | Model: 0.150 Completion: 6.333 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-01-26 |
| Kimi K2.5 Thinking | moonshotai/kimi-k2.5-thinking | 256K | 65.5K | Input: $0.3 Output: $1.9 | Model: 0.150 Completion: 6.333 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-01-26 |
| Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 32.8K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-11-01 Updated: 2025-12-24 |
| Qwen3 Coder | qwen/qwen3-coder | 106K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-15 Updated: 2025-12-24 |
| Qwen3.5 397B A17B | qwen/qwen3.5-397b-a17b | 258K | 8.2K | Input: $0.6 Output: $3.6 | Model: 0.300 Completion: 6.000 | 📎 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2026-02-16 |
| Qwen3.5 397B A17B Thinking | qwen/qwen3.5-397b-a17b-thinking | 258K | 8.2K | Input: $0.6 Output: $3.6 | Model: 0.300 Completion: 6.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2026-02-16 |
| Qwen3 235B A22B Thinking 2507 | qwen/qwen3-235b-a22b-thinking-2507 | 262.1K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-07-01 Updated: 2025-12-24 |
| Qwen3.5 Plus Thinking | qwen/qwen3.5-plus-thinking | 983.6K | 8.2K | Input: $0.4 Output: $2.4 | Model: 0.200 Completion: 6.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2026-02-16 |
| Qwen3.5 Plus | qwen/qwen3.5-plus | 983.6K | 8.2K | Input: $0.4 Output: $2.4 | Model: 0.200 Completion: 6.000 | 📎 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2026-02-16 |
| Llama 3.3 70b Instruct | meta-llama/llama-3.3-70b-instruct | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 Updated: 2025-12-24 |
| Llama 4 Maverick | meta-llama/llama-4-maverick | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-04-05 Updated: 2025-12-24 |
| Mistral Large 3 675b Instruct 2512 | mistralai/mistral-large-3-675b-instruct-2512 | 131.1K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-12-02 Updated: 2025-12-24 |
| Ministral 14b Instruct 2512 | mistralai/ministral-14b-instruct-2512 | 131.1K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-12-01 Updated: 2025-12-24 |
| Devstral 2 123b Instruct 2512 | mistralai/devstral-2-123b-instruct-2512 | 131.1K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-11 Updated: 2025-12-24 |
| GPT Oss 120b | openai/gpt-oss-120b | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-06-23 Updated: 2025-12-24 |
| Minimax M2.1 | minimax/minimax-m2.1 | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-23 Updated: 2025-12-24 |
| MiniMax M2.5 | minimax/minimax-m2.5-official | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-12 |
| MiniMax M2.5 | minimax/minimax-m2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-12 |
| Hermes 4 405b Thinking | nousresearch/hermes-4-405b:thinking | 128K | 8.2K | Input: $1 Output: $2 | Model: 0.500 Completion: 2.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-13 Updated: 2025-12-24 |
Nebius Token Factory¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-4.7 (FP8) | zai-org/glm-4.7-fp8 | 128K | 4.1K | Input: $0.4 Output: $2 Cache Read: $0.04 Cache Write: $0.5 | Model: 0.200 Completion: 5.000 Cache: 0.100 | 🔧 🌡️ | 2025-12 | In: text Out: text | Released: 2026-01-15 Updated: 2026-02-04 |
| GLM-4.5-Air | zai-org/glm-4.5-air | 128K | 4.1K | Input: $0.2 Output: $1.2 Cache Read: $0.02 Cache Write: $0.25 | Model: 0.100 Completion: 6.000 Cache: 0.100 | 🔧 🌡️ | 2025-06 | In: text Out: text | Released: 2025-11-15 Updated: 2026-02-04 |
| GLM-4.5 | zai-org/glm-4.5 | 128K | 4.1K | Input: $0.6 Output: $2.2 Cache Read: $0.06 Cache Write: $0.75 | Model: 0.300 Completion: 3.667 Cache: 0.100 | 🔧 🌡️ | 2025-06 | In: text Out: text | Released: 2025-11-15 Updated: 2026-02-04 |
| Llama-3.1-Nemotron-Ultra-253B-v1 | nvidia/llama-3_1-nemotron-ultra-253b-v1 | 128K | 4.1K | Input: $0.6 Output: $1.8 Cache Read: $0.06 Cache Write: $0.75 | Model: 0.300 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-01-15 Updated: 2026-02-04 |
| Nemotron-Nano-V2-12b | nvidia/nemotron-nano-v2-12b | 32K | 4.1K | Input: $0.07 Output: $0.2 Cache Read: $0.007 Cache Write: $0.08 | Model: 0.035 Completion: 2.857 Cache: 0.100 | 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-03-15 Updated: 2026-02-04 |
| Nemotron-3-Nano-30B-A3B | nvidia/nvidia-nemotron-3-nano-30b-a3b | 32K | 4.1K | Input: $0.06 Output: $0.24 Cache Read: $0.006 Cache Write: $0.075 | Model: 0.030 Completion: 4.000 Cache: 0.100 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-08-10 Updated: 2026-02-04 |
| Hermes-4-405B | NousResearch/hermes-4-405b | 128K | 8.2K | Input: $1 Output: $3 Cache Read: $0.1 Cache Write: $1.25 Reasoning: $3 | Model: 0.500 Completion: 3.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2026-01-30 Updated: 2026-02-04 |
| Hermes-4-70B | NousResearch/hermes-4-70b | 128K | 8.2K | Input: $0.13 Output: $0.4 Cache Read: $0.013 Cache Write: $0.16 Reasoning: $0.4 | Model: 0.065 Completion: 3.077 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2026-01-30 Updated: 2026-02-04 |
| BGE-ICL | BAAI/bge-en-icl | 32.8K | - | Input: $0.01 Output: $0 | Model: 0.005 | - | 2024-06 | In: text Out: text | Open Weights Released: 2024-07-30 Updated: 2026-02-04 |
| bge-multilingual-gemma2 | BAAI/bge-multilingual-gemma2 | 8.2K | - | Input: $0.01 Output: $0 | Model: 0.005 | - | 2024-06 | In: text Out: text | Open Weights Released: 2024-07-30 Updated: 2026-02-04 |
| INTELLECT-3 | PrimeIntellect/intellect-3 | 128K | 8.2K | Input: $0.2 Output: $1.1 Cache Read: $0.02 Cache Write: $0.25 | Model: 0.100 Completion: 5.500 Cache: 0.100 | 🔧 🌡️ | 2025-10 | In: text Out: text | Open Weights Released: 2026-01-25 Updated: 2026-02-04 |
| MiniMax-M2.1 | MiniMaxAI/minimax-m2.1 | 128K | 8.2K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.375 Reasoning: $1.2 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-10 | In: text Out: text | Open Weights Released: 2026-02-01 Updated: 2026-02-04 |
| DeepSeek-V3-0324 (Fast) | deepseek-ai/deepseek-v3-0324-fast | 128K | 8.2K | Input: $0.75 Output: $2.25 Cache Read: $0.075 Cache Write: $0.28125 | Model: 0.375 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-03-24 Updated: 2026-02-04 |
| DeepSeek R1 0528 Fast | deepseek-ai/deepseek-r1-0528-fast | 131.1K | 8.2K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-01-01 Updated: 2025-02-04 |
| DeepSeek-R1-0528 | deepseek-ai/deepseek-r1-0528 | 128K | 32.8K | Input: $0.8 Output: $2.4 Cache Read: $0.08 Cache Write: $1 Reasoning: $2.4 | Model: 0.400 Completion: 3.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2026-01-15 Updated: 2026-02-04 |
| DeepSeek-V3-0324 | deepseek-ai/deepseek-v3-0324 | 128K | 8.2K | Input: $0.5 Output: $1.5 Cache Read: $0.05 Cache Write: $0.1875 | Model: 0.250 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-03-24 Updated: 2026-02-04 |
| DeepSeek-V3.2 | deepseek-ai/deepseek-v3.2 | 128K | 8.2K | Input: $0.3 Output: $0.45 Cache Read: $0.03 Cache Write: $0.375 Reasoning: $0.45 | Model: 0.150 Completion: 1.500 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2026-01-20 Updated: 2026-02-04 |
| e5-mistral-7b-instruct | intfloat/e5-mistral-7b-instruct | 32.8K | - | Input: $0.01 Output: $0 | Model: 0.005 | - | 2023-12 | In: text Out: text | Open Weights Released: 2024-01-01 Updated: 2026-02-04 |
| Kimi-K2-Instruct | moonshotai/kimi-k2-instruct | 200K | 8.2K | Input: $0.5 Output: $2.4 Cache Read: $0.05 Cache Write: $0.625 | Model: 0.250 Completion: 4.800 Cache: 0.100 | 📎 🔧 🌡️ | 2025-10 | In: text, image Out: text | Released: 2026-01-05 Updated: 2026-02-04 |
| Kimi-K2.5 | moonshotai/Kimi-K2.5 | 262.1K | 8.2K | Input: $0.5 Output: $2.5 Cache Read: $0.05 Cache Write: $0.625 Reasoning: $2.5 | Model: 0.250 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-06 | In: text, image Out: text | Open Weights Released: 2025-12-15 Updated: 2026-02-04 |
| Kimi-K2-Thinking | moonshotai/kimi-k2-thinking | 128K | 16.4K | Input: $0.6 Output: $2.5 Cache Read: $0.06 Cache Write: $0.75 Reasoning: $2.5 | Model: 0.300 Completion: 4.167 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-10 | In: text Out: text | Open Weights Released: 2026-01-05 Updated: 2026-02-04 |
| Gemma-2-2b-it | google/gemma-2-2b-it | 8.2K | 4.1K | Input: $0.02 Output: $0.06 Cache Read: $0.002 Cache Write: $0.025 | Model: 0.010 Completion: 3.000 Cache: 0.100 | 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2024-07-31 Updated: 2026-02-04 |
| Gemma-3-27b-it (Fast) | google/gemma-3-27b-it-fast | 128K | 8.2K | Input: $0.2 Output: $0.6 Cache Read: $0.02 Cache Write: $0.25 | Model: 0.100 Completion: 3.000 Cache: 0.100 | 📎 🔧 🌡️ | 2025-10 | In: text, image Out: text | Open Weights Released: 2026-01-20 Updated: 2026-02-04 |
| Gemma-2-9b-it (Fast) | google/gemma-2-9b-it-fast | 8.2K | 4.1K | Input: $0.03 Output: $0.09 Cache Read: $0.003 Cache Write: $0.0375 | Model: 0.015 Completion: 3.000 Cache: 0.100 | 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2024-06-27 Updated: 2026-02-04 |
| Gemma-3-27b-it | google/gemma-3-27b-it | 128K | 8.2K | Input: $0.1 Output: $0.3 Cache Read: $0.01 Cache Write: $0.125 | Model: 0.050 Completion: 3.000 Cache: 0.100 | 📎 🔧 🌡️ | 2025-10 | In: text, image Out: text | Open Weights Released: 2026-01-20 Updated: 2026-02-04 |
| Qwen3 235B A22B Instruct 2507 | qwen/qwen3-235b-a22b-instruct-2507 | 262.1K | 8.2K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-25 Updated: 2025-10-04 |
| Qwen3-Next-80B-A3B-Thinking | qwen/qwen3-next-80b-a3b-thinking | 128K | 16.4K | Input: $0.15 Output: $1.2 Cache Read: $0.015 Cache Write: $0.18 Reasoning: $1.2 | Model: 0.075 Completion: 8.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-28 Updated: 2026-02-04 |
| Qwen2.5-Coder-7B (Fast) | qwen/qwen2.5-coder-7b-fast | 128K | 8.2K | Input: $0.03 Output: $0.09 Cache Read: $0.003 Cache Write: $0.03 | Model: 0.015 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2024-09 | In: text Out: text | Open Weights Released: 2024-09-19 Updated: 2026-02-04 |
| Qwen3 Coder 480B A35B Instruct | qwen/qwen3-coder-480b-a35b-instruct | 262.1K | 66.5K | Input: $0.4 Output: $1.8 | Model: 0.200 Completion: 4.500 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-07-23 Updated: 2025-10-04 |
| Qwen3-Embedding-8B | qwen/qwen3-embedding-8b | 32.8K | - | Input: $0.01 Output: $0 | Model: 0.005 | - | 2025-10 | In: text Out: text | Open Weights Released: 2026-01-10 Updated: 2026-02-04 |
| Qwen3-32B | qwen/qwen3-32b | 128K | 8.2K | Input: $0.1 Output: $0.3 Cache Read: $0.01 Cache Write: $0.125 | Model: 0.050 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-28 Updated: 2026-02-04 |
| Qwen3-30B-A3B-Instruct-2507 | qwen/qwen3-30b-a3b-instruct-2507 | 128K | 8.2K | Input: $0.1 Output: $0.3 Cache Read: $0.01 Cache Write: $0.125 | Model: 0.050 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-28 Updated: 2026-02-04 |
| Qwen2.5-VL-72B-Instruct | qwen/qwen2.5-vl-72b-instruct | 128K | 8.2K | Input: $0.25 Output: $0.75 Cache Read: $0.025 Cache Write: $0.31 | Model: 0.125 Completion: 3.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-12 | In: text, image Out: text | Open Weights Released: 2025-01-20 Updated: 2026-02-04 |
| Qwen3-Coder-30B-A3B-Instruct | qwen/qwen3-coder-30b-a3b-instruct | 128K | 8.2K | Input: $0.1 Output: $0.3 Cache Read: $0.01 Cache Write: $0.125 | Model: 0.050 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-28 Updated: 2026-02-04 |
| Qwen3-30B-A3B-Thinking-2507 | qwen/qwen3-30b-a3b-thinking-2507 | 128K | 16.4K | Input: $0.1 Output: $0.3 Cache Read: $0.01 Cache Write: $0.125 Reasoning: $0.3 | Model: 0.050 Completion: 3.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-28 Updated: 2026-02-04 |
| Qwen3-32B (Fast) | qwen/qwen3-32b-fast | 128K | 8.2K | Input: $0.2 Output: $0.6 Cache Read: $0.02 Cache Write: $0.25 | Model: 0.100 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2026-01-28 Updated: 2026-02-04 |
| Qwen3 235B A22B Thinking 2507 | qwen/qwen3-235b-a22b-thinking-2507 | 262.1K | 8.2K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-25 Updated: 2025-10-04 |
| Llama-Guard-3-8B | meta-llama/llama-guard-3-8b | 8.2K | 1K | Input: $0.02 Output: $0.06 Cache Read: $0.002 Cache Write: $0.025 | Model: 0.010 Completion: 3.000 Cache: 0.100 | - | 2024-04 | In: text Out: text | Open Weights Released: 2024-04-18 Updated: 2026-02-04 |
| Meta-Llama-3.1-8B-Instruct | meta-llama/meta-llama-3.1-8b-instruct | 128K | 4.1K | Input: $0.02 Output: $0.06 Cache Read: $0.002 Cache Write: $0.025 | Model: 0.010 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2024-07-23 Updated: 2026-02-04 |
| Llama-3.3-70B-Instruct | meta-llama/Llama-3.3-70B-Instruct | 128K | 8.2K | Input: $0.13 Output: $0.4 Cache Read: $0.013 Cache Write: $0.16 | Model: 0.065 Completion: 3.077 Cache: 0.100 | 🔧 🌡️ | 2025-08 | In: text Out: text | Open Weights Released: 2025-12-05 Updated: 2026-02-04 |
| Llama-3.3-70B-Instruct (Fast) | meta-llama/llama-3.3-70b-instruct-fast | 128K | 8.2K | Input: $0.25 Output: $0.75 Cache Read: $0.025 Cache Write: $0.31 | Model: 0.125 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2025-08 | In: text Out: text | Open Weights Released: 2025-12-05 Updated: 2026-02-04 |
| Meta-Llama-3.1-8B-Instruct (Fast) | meta-llama/meta-llama-3.1-8b-instruct-fast | 128K | 4.1K | Input: $0.03 Output: $0.09 Cache Read: $0.003 Cache Write: $0.03 | Model: 0.015 Completion: 3.000 Cache: 0.100 | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2024-07-23 Updated: 2026-02-04 |
| gpt-oss-120b | openai/gpt-oss-120b | 128K | 8.2K | Input: $0.15 Output: $0.6 Cache Read: $0.015 Cache Write: $0.18 Reasoning: $0.6 | Model: 0.075 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2026-01-10 Updated: 2026-02-04 |
| gpt-oss-20b | openai/gpt-oss-20b | 128K | 4.1K | Input: $0.05 Output: $0.2 Cache Read: $0.005 Cache Write: $0.06 | Model: 0.025 Completion: 4.000 Cache: 0.100 | 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2026-01-10 Updated: 2026-02-04 |
| FLUX.1-dev | black-forest-labs/flux-dev | 77 | - | Input: $0 Output: $0 | - | - | 2024-07 | In: text Out: image | Open Weights Released: 2024-08-01 Updated: 2026-02-04 |
| FLUX.1-schnell | black-forest-labs/flux-schnell | 77 | - | Input: $0 Output: $0 | - | - | 2024-07 | In: text Out: image | Open Weights Released: 2024-08-01 Updated: 2026-02-04 |
Nova¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Nova 2 Lite | nova-2-lite-v1 | 1M | 64K | Input: $0 Output: $0 Reasoning: $0 | - | 📎 🧠 🔧 🌡️ | - | In: text, image, video, pdf Out: text | Released: 2025-12-01 |
| Nova 2 Pro | nova-2-pro-v1 | 1M | 64K | Input: $0 Output: $0 Reasoning: $0 | - | 📎 🧠 🔧 🌡️ | - | In: text, image, video, pdf Out: text | Released: 2025-12-03 Updated: 2026-01-03 |
NovitaAI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5 | zai-org/glm-5 | 202.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-11 Updated: 2026-02-12 |
| GLM 4.5 Air | zai-org/glm-4.5-air | 131.1K | 98.3K | Input: $0.13 Output: $0.85 | Model: 0.065 Completion: 6.538 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-10-13 |
| GLM-4.5 | zai-org/glm-4.5 | 131.1K | 98.3K | Input: $0.6 Output: $2.2 Cache Read: $0.11 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.7-Flash | zai-org/glm-4.7-flash | 200K | 128K | Input: $0.07 Output: $0.4 Cache Read: $0.01 | Model: 0.035 Completion: 5.714 Cache: 0.143 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-01-19 |
| GLM 4.6 | zai-org/glm-4.6 | 204.8K | 131.1K | Input: $0.55 Output: $2.2 Cache Read: $0.11 | Model: 0.275 Completion: 4.000 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7 | zai-org/glm-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.11 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-22 |
| AutoGLM-Phone-9B-Multilingual | zai-org/autoglm-phone-9b-multilingual | 65.5K | 65.5K | Input: $0.035 Output: $0.138 | Model: 0.018 Completion: 3.943 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-12-10 |
| GLM 4.5V | zai-org/glm-4.5v | 65.5K | 16.4K | Input: $0.6 Output: $1.8 Cache Read: $0.11 | Model: 0.300 Completion: 3.000 Cache: 0.183 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, video, image Out: text | Open Weights Released: 2025-08-11 |
| GLM 4.6V | zai-org/glm-4.6v | 131.1K | 32.8K | Input: $0.3 Output: $0.9 Cache Read: $0.055 | Model: 0.150 Completion: 3.000 Cache: 0.183 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, video, image Out: text | Open Weights Released: 2025-12-08 |
| Wizardlm 2 8x22B | microsoft/wizardlm-2-8x22b | 65.5K | 8K | Input: $0.62 Output: $0.62 | Model: 0.310 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-24 |
| MiniMax M1 | minimaxai/minimax-m1-80k | 1M | 40K | Input: $0.55 Output: $2.2 | Model: 0.275 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-17 |
| Skywork R1V4-Lite | skywork/r1v4-lite | 262.1K | 65.5K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-11-18 |
| Mythomax L2 13B | gryphe/mythomax-l2-13b | 4.1K | 3.2K | Input: $0.09 Output: $0.09 | Model: 0.045 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-25 |
| PaddleOCR-VL | paddlepaddle/paddleocr-vl | 16.4K | 16.4K | Input: $0.02 Output: $0.02 | Model: 0.010 Completion: 1.000 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-10-22 |
| baichuan-m2-32b | baichuan/baichuan-m2-32b | 131.1K | 131.1K | Input: $0.07 Output: $0.07 | Model: 0.035 Completion: 1.000 | 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-08-13 |
| Kat Coder Pro | kwaipilot/kat-coder-pro | 256K | 128K | Input: $0.3 Output: $1.2 Cache Read: $0.06 | Model: 0.150 Completion: 4.000 Cache: 0.200 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-05 |
| KAT-Coder-Pro V1(Free) | kwaipilot/kat-coder | 256K | 32K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-30 |
| **DeepSeek V3 (Turbo) ** | deepseek/deepseek-v3-turbo | 64K | 16K | Input: $0.4 Output: $1.3 | Model: 0.200 Completion: 3.250 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-05 |
| Deepseek Prover V2 671B | deepseek/deepseek-prover-v2-671b | 160K | 160K | Input: $0.7 Output: $2.5 | Model: 0.350 Completion: 3.571 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-30 |
| **DeepSeek R1 (Turbo) ** | deepseek/deepseek-r1-turbo | 64K | 16K | Input: $0.7 Output: $2.5 | Model: 0.350 Completion: 3.571 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-05 |
| deepseek/deepseek-ocr-2 | deepseek/deepseek-ocr-2 | 8.2K | 8.2K | Input: $0.03 Output: $0.03 | Model: 0.015 Completion: 1.000 | 📎 | - | In: text, image Out: text | Open Weights Released: 2026-01-27 |
| DeepSeek V3.1 | deepseek/deepseek-v3.1 | 131.1K | 32.8K | Input: $0.27 Output: $1 Cache Read: $0.135 | Model: 0.135 Completion: 3.704 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-21 |
| DeepSeek R1 0528 | deepseek/deepseek-r1-0528 | 163.8K | 32.8K | Input: $0.7 Output: $2.5 Cache Read: $0.35 | Model: 0.350 Completion: 3.571 Cache: 0.500 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek R1 0528 Qwen3 8B | deepseek/deepseek-r1-0528-qwen3-8b | 128K | 32K | Input: $0.06 Output: $0.09 | Model: 0.030 Completion: 1.500 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-05-29 |
| DeepSeek R1 Distill LLama 70B | deepseek/deepseek-r1-distill-llama-70b | 8.2K | 8.2K | Input: $0.8 Output: $0.8 | Model: 0.400 Completion: 1.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-27 |
| DeepSeek V3 0324 | deepseek/deepseek-v3-0324 | 163.8K | 163.8K | Input: $0.27 Output: $1.12 Cache Read: $0.135 | Model: 0.135 Completion: 4.148 Cache: 0.500 | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-03-25 |
| Deepseek V3.1 Terminus | deepseek/deepseek-v3.1-terminus | 131.1K | 32.8K | Input: $0.27 Output: $1 Cache Read: $0.135 | Model: 0.135 Completion: 3.704 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-22 |
| Deepseek V3.2 | deepseek/deepseek-v3.2 | 163.8K | 65.5K | Input: $0.269 Output: $0.4 Cache Read: $0.1345 | Model: 0.135 Completion: 1.487 Cache: 0.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-01 |
| DeepSeek-OCR | deepseek/deepseek-ocr | 8.2K | 8.2K | Input: $0.03 Output: $0.03 | Model: 0.015 Completion: 1.000 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-10-24 |
| Deepseek V3.2 Exp | deepseek/deepseek-v3.2-exp | 163.8K | 65.5K | Input: $0.27 Output: $0.41 | Model: 0.135 Completion: 1.519 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-29 |
| Kimi K2 Instruct | moonshotai/kimi-k2-instruct | 131.1K | 131.1K | Input: $0.57 Output: $2.3 | Model: 0.285 Completion: 4.035 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-11 |
| Kimi K2 0905 | moonshotai/kimi-k2-0905 | 262.1K | 262.1K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2.5 | moonshotai/kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 Cache Read: $0.1 | Model: 0.300 Completion: 5.000 Cache: 0.167 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-11-07 |
| ERNIE-4.5-VL-28B-A3B-Thinking | baidu/ernie-4.5-vl-28b-a3b-thinking | 131.1K | 65.5K | Input: $0.39 Output: $0.39 | Model: 0.195 Completion: 1.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2025-11-26 |
| ERNIE 4.5 VL 424B A47B | baidu/ernie-4.5-vl-424b-a47b | 123K | 16K | Input: $0.42 Output: $1.25 | Model: 0.210 Completion: 2.976 | 📎 🧠 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-06-30 |
| ERNIE 4.5 VL 28B A3B | baidu/ernie-4.5-vl-28b-a3b | 30K | 8K | Input: $1.4 Output: $5.6 | Model: 0.700 Completion: 4.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-06-30 |
| ERNIE 4.5 300B A47B | baidu/ernie-4.5-300b-a47b-paddle | 123K | 12K | Input: $0.28 Output: $1.1 | Model: 0.140 Completion: 3.929 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-30 |
| ERNIE 4.5 21B A3B | baidu/ernie-4.5-21B-a3b | 120K | 8K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | 2025-03 | In: text Out: text | Open Weights Released: 2025-06-30 |
| ERNIE-4.5-21B-A3B-Thinking | baidu/ernie-4.5-21B-a3b-thinking | 131.1K | 65.5K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🧠 🌡️ | 2025-03 | In: text Out: text | Open Weights Released: 2025-09-19 |
| Gemma 3 27B | google/gemma-3-27b-it | 98.3K | 16.4K | Input: $0.119 Output: $0.2 | Model: 0.059 Completion: 1.681 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-25 |
| Qwen3 4B | qwen/qwen3-4b-fp8 | 128K | 20K | Input: $0.03 Output: $0.03 | Model: 0.015 Completion: 1.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-29 |
| Qwen3 235B A22B Instruct 2507 | qwen/qwen3-235b-a22b-instruct-2507 | 131.1K | 16.4K | Input: $0.09 Output: $0.58 | Model: 0.045 Completion: 6.444 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-22 |
| Qwen3 32B | qwen/qwen3-32b-fp8 | 41K | 20K | Input: $0.1 Output: $0.45 | Model: 0.050 Completion: 4.500 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-29 |
| Qwen3 Next 80B A3B Thinking | qwen/qwen3-next-80b-a3b-thinking | 131.1K | 32.8K | Input: $0.15 Output: $1.5 | Model: 0.075 Completion: 10.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-10 |
| Qwen3 Coder 480B A35B Instruct | qwen/qwen3-coder-480b-a35b-instruct | 262.1K | 65.5K | Input: $0.3 Output: $1.3 | Model: 0.150 Completion: 4.333 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen3 30B A3B | qwen/qwen3-30b-a3b-fp8 | 41K | 20K | Input: $0.09 Output: $0.45 | Model: 0.045 Completion: 5.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-29 |
| Qwen3 Coder Next | qwen/qwen3-coder-next | 262.1K | 65.5K | Input: $0.2 Output: $1.5 | Model: 0.100 Completion: 7.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-03 |
| Qwen3.5-397B-A17B | qwen/qwen3.5-397b-a17b | 262.1K | 64K | Input: $0.6 Output: $3.6 | Model: 0.300 Completion: 6.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2026-02-17 |
| Qwen2.5 VL 72B Instruct | qwen/qwen2.5-vl-72b-instruct | 32.8K | 32.8K | Input: $0.8 Output: $0.8 | Model: 0.400 Completion: 1.000 | 📎 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2025-03-25 |
| Qwen3 Coder 30b A3B Instruct | qwen/qwen3-coder-30b-a3b-instruct | 160K | 32.8K | Input: $0.07 Output: $0.27 | Model: 0.035 Completion: 3.857 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-09 |
| Qwen3 VL 235B A22B Instruct | qwen/qwen3-vl-235b-a22b-instruct | 131.1K | 32.8K | Input: $0.3 Output: $1.5 | Model: 0.150 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2025-09-24 |
| Qwen MT Plus | qwen/qwen-mt-plus | 16.4K | 8.2K | Input: $0.25 Output: $0.75 | Model: 0.125 Completion: 3.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-03 |
| Qwen3 Omni 30B A3B Instruct | qwen/qwen3-omni-30b-a3b-instruct | 65.5K | 16.4K | Input: $0.25 Output: $0.97 Input Audio: $2.2 Output Audio: $1.788 | Model: 1.100 Completion: 0.813 | 📎 🔧 🌡️ | 2024-04 | In: text, video, audio, image Out: text, audio | Open Weights Released: 2025-09-24 |
| Qwen 2.5 72B Instruct | qwen/qwen-2.5-72b-instruct | 32K | 8.2K | Input: $0.38 Output: $0.4 | Model: 0.190 Completion: 1.053 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-10-15 |
| qwen/qwen3-vl-30b-a3b-thinking | qwen/qwen3-vl-30b-a3b-thinking | 131.1K | 32.8K | Input: $0.2 Output: $1 | Model: 0.100 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2025-10-11 |
| Qwen3 VL 235B A22B Thinking | qwen/qwen3-vl-235b-a22b-thinking | 131.1K | 32.8K | Input: $0.98 Output: $3.95 | Model: 0.490 Completion: 4.031 | 📎 🧠 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2025-09-24 |
| Qwen3 235B A22b Thinking 2507 | qwen/qwen3-235b-a22b-thinking-2507 | 131.1K | 32.8K | Input: $0.3 Output: $3 | Model: 0.150 Completion: 10.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen2.5 7B Instruct | qwen/qwen2.5-7b-instruct | 32K | 32K | Input: $0.07 Output: $0.07 | Model: 0.035 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-16 |
| qwen/qwen3-vl-30b-a3b-instruct | qwen/qwen3-vl-30b-a3b-instruct | 131.1K | 32.8K | Input: $0.2 Output: $0.7 | Model: 0.100 Completion: 3.500 | 📎 🔧 🌡️ | - | In: text, video, image Out: text | Open Weights Released: 2025-10-11 |
| Qwen3 Next 80B A3B Instruct | qwen/qwen3-next-80b-a3b-instruct | 131.1K | 32.8K | Input: $0.15 Output: $1.5 | Model: 0.075 Completion: 10.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-09-10 |
| Qwen3 235B A22B | qwen/qwen3-235b-a22b-fp8 | 41K | 20K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-29 |
| qwen/qwen3-vl-8b-instruct | qwen/qwen3-vl-8b-instruct | 131.1K | 32.8K | Input: $0.08 Output: $0.5 | Model: 0.040 Completion: 6.250 | 📎 🔧 🌡️ | - | In: text, image, video Out: text | Open Weights Released: 2025-10-17 |
| Qwen3 Max | qwen/qwen3-max | 262.1K | 65.5K | Input: $2.11 Output: $8.45 | Model: 1.055 Completion: 4.005 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-09-24 |
| Qwen3 8B | qwen/qwen3-8b-fp8 | 128K | 20K | Input: $0.035 Output: $0.138 | Model: 0.018 Completion: 3.943 | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-29 |
| Qwen3 Omni 30B A3B Thinking | qwen/qwen3-omni-30b-a3b-thinking | 65.5K | 16.4K | Input: $0.25 Output: $0.97 Input Audio: $2.2 Output Audio: $1.788 | Model: 1.100 Completion: 0.813 | 📎 🧠 🔧 🌡️ | - | In: text, audio, video, image Out: text | Open Weights Released: 2025-09-24 |
| Llama 3.3 70B Instruct | meta-llama/llama-3.3-70b-instruct | 131.1K | 120K | Input: $0.135 Output: $0.4 | Model: 0.068 Completion: 2.963 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-07 |
| Llama 4 Scout Instruct | meta-llama/llama-4-scout-17b-16e-instruct | 131.1K | 131.1K | Input: $0.18 Output: $0.59 | Model: 0.090 Completion: 3.278 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-04-06 |
| Llama3 70B Instruct | meta-llama/llama-3-70b-instruct | 8.2K | 8K | Input: $0.51 Output: $0.74 | Model: 0.255 Completion: 1.451 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-25 |
| Llama 3.1 8B Instruct | meta-llama/llama-3.1-8b-instruct | 16.4K | 16.4K | Input: $0.02 Output: $0.05 | Model: 0.010 Completion: 2.500 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-24 |
| Llama 3 8B Instruct | meta-llama/llama-3-8b-instruct | 8.2K | 8.2K | Input: $0.04 Output: $0.04 | Model: 0.020 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-25 |
| Llama 4 Maverick Instruct | meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | 1M | 8.2K | Input: $0.27 Output: $0.85 | Model: 0.135 Completion: 3.148 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-04-06 |
| Mistral Nemo | mistralai/mistral-nemo | 60.3K | 16K | Input: $0.04 Output: $0.17 | Model: 0.020 Completion: 4.250 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-30 |
| OpenAI GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 32.8K | Input: $0.05 Output: $0.25 | Model: 0.025 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-08-06 |
| OpenAI: GPT OSS 20B | openai/gpt-oss-20b | 131.1K | 32.8K | Input: $0.04 Output: $0.15 | Model: 0.020 Completion: 3.750 | 📎 🧠 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-08-06 |
| Minimax M2.1 | minimax/minimax-m2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| MiniMax-M2 | minimax/minimax-m2 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-27 |
| MiniMax M2.5 | minimax/minimax-m2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-12 |
| **L3 70B Euryale V2.1 ** | sao10k/l3-70b-euryale-v2.1 | 8.2K | 8.2K | Input: $1.48 Output: $1.48 | Model: 0.740 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-06-18 |
| L31 70B Euryale V2.2 | sao10k/l31-70b-euryale-v2.2 | 8.2K | 8.2K | Input: $1.48 Output: $1.48 | Model: 0.740 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09-19 |
| **Sao10k L3 8B Lunaris ** | sao10k/l3-8b-lunaris | 8.2K | 8.2K | Input: $0.05 Output: $0.05 | Model: 0.025 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-28 |
| L3 8B Stheno V3.2 | sao10k/L3-8B-Stheno-v3.2 | 8.2K | 32K | Input: $0.05 Output: $0.05 | Model: 0.025 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-29 |
| XiaomiMiMo/MiMo-V2-Flash | xiaomimimo/mimo-v2-flash | 262.1K | 32K | Input: $0.1 Output: $0.3 Cache Read: $0.3 | Model: 0.050 Completion: 3.000 Cache: 3.000 | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-12-19 |
| Hermes 2 Pro Llama 3 8B | nousresearch/hermes-2-pro-llama-3-8b | 8.2K | 8.2K | Input: $0.14 Output: $0.14 | Model: 0.070 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-06-27 |
Nvidia¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Llama 3.1 Nemotron 70b Instruct | nvidia/llama-3.1-nemotron-70b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Released: 2024-10-12 |
| Llama-3.1-Nemotron-Ultra-253B-v1 | nvidia/llama-3.1-nemotron-ultra-253b-v1 | 131.1K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-07-01 Updated: 2025-09-05 |
| Llama 3.1 Nemotron 51b Instruct | nvidia/llama-3.1-nemotron-51b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-22 |
| Parakeet TDT 0.6B v2 | nvidia/parakeet-tdt-0.6b-v2 | - | 4.1K | Input: $0 Output: $0 | - | - | 2024-01 | In: audio Out: text | Released: 2024-01-01 Updated: 2025-09-05 |
| nvidia-nemotron-nano-9b-v2 | nvidia/nvidia-nemotron-nano-9b-v2 | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-09 | In: text Out: text | Open Weights Released: 2025-08-18 |
| Llama Embed Nemotron 8B | nvidia/llama-embed-nemotron-8b | 32.8K | 2K | Input: $0 Output: $0 | - | - | 2025-03 | In: text Out: text | Released: 2025-03-18 |
| Llama 3.3 Nemotron Super 49b V1.5 | nvidia/llama-3.3-nemotron-super-49b-v1.5 | 128K | 4.1K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-03-16 |
| Llama 3.3 Nemotron Super 49b V1 | nvidia/llama-3.3-nemotron-super-49b-v1 | 128K | 4.1K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Released: 2025-03-16 |
| Llama3 Chatqa 1.5 70b | nvidia/llama3-chatqa-1.5-70b | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Released: 2024-04-28 |
| Cosmos Nemotron 34B | nvidia/cosmos-nemotron-34b | 131.1K | 8.2K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2024-01 | In: text, image, video Out: text | Released: 2024-01-01 Updated: 2025-09-05 |
| NeMo Retriever OCR v1 | nvidia/nemoretriever-ocr-v1 | - | 4.1K | Input: $0 Output: $0 | - | - | 2024-01 | In: image Out: text | Released: 2024-01-01 Updated: 2025-09-05 |
| Nemotron 4 340b Instruct | nvidia/nemotron-4-340b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Released: 2024-06-13 |
| nemotron-3-nano-30b-a3b | nvidia/nemotron-3-nano-30b-a3b | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-09 | In: text Out: text | Open Weights Released: 2024-12 |
| Phi 3 Small 128k Instruct | microsoft/phi-3-small-128k-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-10 | In: text, image Out: text | Open Weights Released: 2024-05-07 |
| Phi 3 Medium 128k Instruct | microsoft/phi-3-medium-128k-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-10 | In: text, image Out: text | Open Weights Released: 2024-05-07 |
| Phi 3.5 Moe Instruct | microsoft/phi-3.5-moe-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-08-17 |
| Phi 3 Vision 128k Instruct | microsoft/phi-3-vision-128k-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2024-05-19 |
| Phi-4-Mini | microsoft/phi-4-mini-instruct | 131.1K | 8.2K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2024-12 | In: text, image, audio Out: text | Released: 2024-12-01 Updated: 2025-09-05 |
| Phi 3.5 Vision Instruct | microsoft/phi-3.5-vision-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2024-08-16 |
| Phi 3 Medium 4k Instruct | microsoft/phi-3-medium-4k-instruct | 4K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-10 | In: text, image Out: text | Open Weights Released: 2024-05-07 |
| Phi 3 Small 8k Instruct | microsoft/phi-3-small-8k-instruct | 8K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-10 | In: text, image Out: text | Open Weights Released: 2024-05-07 |
| MiniMax-M2.1 | minimaxai/minimax-m2.1 | 204.8K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| MiniMax-M2 | minimaxai/minimax-m2 | 128K | 16.4K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-10-27 Updated: 2025-10-31 |
| DeepSeek V3.1 | deepseek-ai/deepseek-v3.1 | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-08-20 Updated: 2025-08-26 |
| Deepseek R1 0528 | deepseek-ai/deepseek-r1-0528 | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-05-28 |
| Deepseek R1 | deepseek-ai/deepseek-r1 | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-20 |
| DeepSeek V3.1 Terminus | deepseek-ai/deepseek-v3.1-terminus | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Released: 2025-09-22 |
| Deepseek Coder 6.7b Instruct | deepseek-ai/deepseek-coder-6.7b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2023-10-29 |
| DeepSeek V3.2 | deepseek-ai/deepseek-v3.2 | 163.8K | 65.5K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-12-01 |
| Kimi K2 Instruct | moonshotai/kimi-k2-instruct | 128K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-01 | In: text Out: text | Released: 2025-01-01 Updated: 2025-09-05 |
| Kimi K2 0905 | moonshotai/kimi-k2-instruct-0905 | 262.1K | 262.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2.5 | moonshotai/kimi-k2.5 | 262.1K | 262.1K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-07 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 262.1K | 262.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-11 Updated: 2025-12 |
| Codegemma 7b | google/codegemma-7b | 128K | 4.1K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-03-21 |
| Gemma 2 2b It | google/gemma-2-2b-it | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-16 |
| Gemma 3 1b It | google/gemma-3-1b-it | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-10 |
| Gemma 2 27b It | google/gemma-2-27b-it | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-06-24 |
| Gemma 3n E2b It | google/gemma-3n-e2b-it | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-06 | In: text, image Out: text | Open Weights Released: 2025-06-12 |
| Codegemma 1.1 7b | google/codegemma-1.1-7b | 128K | 4.1K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-30 |
| Gemma 3n E4b It | google/gemma-3n-e4b-it | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-06 | In: text, image Out: text | Open Weights Released: 2025-06-03 |
| Gemma 3 12b It | google/gemma-3-12b-it | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-01 |
| Gemma-3-27B-IT | google/gemma-3-27b-it | 131.1K | 8.2K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2024-12 | In: text, image Out: text | Released: 2024-12-01 Updated: 2025-09-05 |
| GLM-4.7 | z-ai/glm4.7 | 204.8K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM5 | z-ai/glm5 | 202.8K | 131K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| Qwen3-Next-80B-A3B-Thinking | qwen/qwen3-next-80b-a3b-thinking | 262.1K | 16.4K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2024-12-01 Updated: 2025-09-05 |
| Qwen3 Coder 480B A35B Instruct | qwen/qwen3-coder-480b-a35b-instruct | 262.1K | 66.5K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-07-23 |
| Qwq 32b | qwen/qwq-32b | 128K | 4.1K | Input: $0 Output: $0 | - | 🧠 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-05 |
| Qwen2.5 Coder 7b Instruct | qwen/qwen2.5-coder-7b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-09-17 |
| Qwen2.5 Coder 32b Instruct | qwen/qwen2.5-coder-32b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-06 |
| Qwen3-235B-A22B | qwen/qwen3-235b-a22b | 131.1K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2024-12-01 Updated: 2025-09-05 |
| Qwen3-Next-80B-A3B-Instruct | qwen/qwen3-next-80b-a3b-instruct | 262.1K | 16.4K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-12 | In: text Out: text | Released: 2024-12-01 Updated: 2025-09-05 |
| Llama 3.1 70b Instruct | meta/llama-3.1-70b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-16 |
| Llama 3.3 70b Instruct | meta/llama-3.3-70b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-26 |
| Llama 4 Scout 17b 16e Instruct | meta/llama-4-scout-17b-16e-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-02 | In: text, image Out: text | Open Weights Released: 2025-04-02 |
| Llama 3.2 11b Vision Instruct | meta/llama-3.2-11b-vision-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-18 |
| Llama3 8b Instruct | meta/llama3-8b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-17 |
| Codellama 70b | meta/codellama-70b | 128K | 4.1K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-01-29 |
| Llama 3.2 1b Instruct | meta/llama-3.2-1b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-09-18 |
| Llama 3.1 405b Instruct | meta/llama-3.1-405b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-16 |
| Llama3 70b Instruct | meta/llama3-70b-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-04-17 |
| Llama 4 Maverick 17b 128e Instruct | meta/llama-4-maverick-17b-128e-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-02 | In: text, image Out: text | Open Weights Released: 2025-04-01 |
| Mistral Large 3 675B Instruct 2512 | mistralai/mistral-large-3-675b-instruct-2512 | 262.1K | 262.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-01 | In: text, image Out: text | Open Weights Released: 2025-12-02 |
| Mamba Codestral 7b V0.1 | mistralai/mamba-codestral-7b-v0.1 | 128K | 4.1K | Input: $0 Output: $0 | - | 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-16 |
| Codestral 22b Instruct V0.1 | mistralai/codestral-22b-instruct-v0.1 | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-05-29 |
| Mistral Large 2 Instruct | mistralai/mistral-large-2-instruct | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-24 |
| Ministral 3 14B Instruct 2512 | mistralai/ministral-14b-instruct-2512 | 262.1K | 262.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-12 | In: text, image Out: text | Open Weights Released: 2025-12-01 Updated: 2025-12-08 |
| Mistral Small 3.1 24b Instruct 2503 | mistralai/mistral-small-3.1-24b-instruct-2503 | 128K | 4.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-11 |
| Devstral-2-123B-Instruct-2512 | mistralai/devstral-2-123b-instruct-2512 | 262.1K | 262.1K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-12-08 Updated: 2025-12-09 |
| GPT-OSS-120B | openai/gpt-oss-120b | 128K | 8.2K | Input: $0 Output: $0 | - | 📎 🧠 🌡️ | 2025-08 | In: text Out: text | Released: 2025-08-04 Updated: 2025-08-14 |
| Whisper Large v3 | openai/whisper-large-v3 | - | 4.1K | Input: $0 Output: $0 | - | - | 2023-09 | In: audio Out: text | Open Weights Released: 2023-09-01 Updated: 2025-09-05 |
| FLUX.1-dev | black-forest-labs/flux.1-dev | 4.1K | - | Input: $0 Output: $0 | - | 🌡️ | 2024-08 | In: text Out: image | Released: 2024-08-01 Updated: 2025-09-05 |
Ollama Cloud¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| glm-5 | glm-5 | 202.8K | 131.1K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2026-02-11 |
| qwen3-coder:480b | qwen3-coder:480b | 262.1K | 65.5K | - | - | 🔧 | - | In: text Out: text | Open Weights Released: 2025-07-22 Updated: 2026-01-19 |
| nemotron-3-nano:30b | nemotron-3-nano:30b | 1M | 131.1K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-12-15 Updated: 2026-01-19 |
| ministral-3:8b | ministral-3:8b | 262.1K | 128K | - | - | 📎 🔧 | - | In: text, image Out: text | Open Weights Released: 2024-12-01 Updated: 2026-01-19 |
| qwen3-coder-next | qwen3-coder-next | 262.1K | 65.5K | - | - | 🔧 | - | In: text Out: text | Open Weights Released: 2026-02-02 Updated: 2026-02-08 |
| gpt-oss:120b | gpt-oss:120b | 131.1K | 32.8K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-08-05 Updated: 2026-01-19 |
| devstral-2:123b | devstral-2:123b | 262.1K | 262.1K | - | - | 🔧 | - | In: text Out: text | Open Weights Released: 2025-12-09 Updated: 2026-01-19 |
| glm-4.6 | glm-4.6 | 202.8K | 131.1K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-09-29 Updated: 2026-01-19 |
| qwen3-vl:235b-instruct | qwen3-vl:235b-instruct | 262.1K | 131.1K | - | - | 📎 🔧 | - | In: text, image Out: text | Open Weights Released: 2025-09-22 Updated: 2026-01-19 |
| gemini-3-flash-preview | gemini-3-flash-preview | 1M | 65.5K | - | - | 🧠 🔧 | 2025-01 | In: text Out: text | Open Weights Released: 2025-12-17 Updated: 2026-01-19 |
| minimax-m2.1 | minimax-m2.1 | 204.8K | 131.1K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-12-23 Updated: 2026-01-19 |
| ministral-3:14b | ministral-3:14b | 262.1K | 128K | - | - | 📎 🔧 | - | In: text, image Out: text | Open Weights Released: 2024-12-01 Updated: 2026-01-19 |
| qwen3-next:80b | qwen3-next:80b | 262.1K | 32.8K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-09-15 Updated: 2026-01-19 |
| kimi-k2:1t | kimi-k2:1t | 262.1K | 262.1K | - | - | 🔧 | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-11 Updated: 2026-01-19 |
| gemma3:12b | gemma3:12b | 131.1K | 131.1K | - | - | 📎 | - | In: text, image Out: text | Open Weights Released: 2024-12-01 Updated: 2026-01-19 |
| kimi-k2.5 | kimi-k2.5 | 262.1K | 262.1K | - | - | 📎 🧠 🔧 | - | In: text, image Out: text | Open Weights Released: 2026-01-27 |
| gpt-oss:20b | gpt-oss:20b | 131.1K | 32.8K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-08-05 Updated: 2026-01-19 |
| deepseek-v3.2 | deepseek-v3.2 | 163.8K | 65.5K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-06-15 Updated: 2026-01-19 |
| glm-4.7 | glm-4.7 | 202.8K | 131.1K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-12-22 Updated: 2026-01-19 |
| kimi-k2-thinking | kimi-k2-thinking | 262.1K | 262.1K | - | - | 🧠 🔧 | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 Updated: 2026-01-19 |
| ministral-3:3b | ministral-3:3b | 262.1K | 128K | - | - | 📎 🔧 | - | In: text, image Out: text | Open Weights Released: 2024-10-22 Updated: 2026-01-19 |
| qwen3.5:397b | qwen3.5:397b | 262.1K | 81.9K | - | - | 📎 🧠 🔧 | - | In: text, image Out: text | Open Weights Released: 2026-02-15 Updated: 2026-02-17 |
| gemma3:27b | gemma3:27b | 131.1K | 131.1K | - | - | 📎 | - | In: text, image Out: text | Open Weights Released: 2025-07-27 Updated: 2026-01-19 |
| minimax-m2 | minimax-m2 | 204.8K | 128K | - | - | 🔧 | - | In: text Out: text | Open Weights Released: 2025-10-23 Updated: 2026-01-19 |
| minimax-m2.5 | minimax-m2.5 | 204.8K | 131.1K | - | - | 🧠 🔧 | 2025-01 | In: text Out: text | Open Weights Released: 2026-02-12 |
| gemini-3-pro-preview | gemini-3-pro-preview | 1M | 64K | - | - | 📎 🧠 🔧 | - | In: text, image Out: text | Open Weights Released: 2025-11-18 Updated: 2026-01-19 |
| devstral-small-2:24b | devstral-small-2:24b | 262.1K | 262.1K | - | - | 📎 🔧 | - | In: text, image Out: text | Open Weights Released: 2025-12-09 Updated: 2026-01-19 |
| cogito-2.1:671b | cogito-2.1:671b | 163.8K | 32K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-11-19 Updated: 2026-01-19 |
| gemma3:4b | gemma3:4b | 131.1K | 131.1K | - | - | 📎 | - | In: text, image Out: text | Open Weights Released: 2024-12-01 Updated: 2026-01-19 |
| deepseek-v3.1:671b | deepseek-v3.1:671b | 163.8K | 163.8K | - | - | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-08-21 Updated: 2026-01-19 |
| mistral-large-3:675b | mistral-large-3:675b | 262.1K | 262.1K | - | - | 📎 🔧 | - | In: text, image Out: text | Open Weights Released: 2025-12-02 Updated: 2026-01-19 |
| rnj-1:8b | rnj-1:8b | 32.8K | 4.1K | - | - | 🔧 | - | In: text Out: text | Open Weights Released: 2025-12-06 Updated: 2026-01-19 |
| qwen3-vl:235b | qwen3-vl:235b | 262.1K | 32.8K | - | - | 📎 🧠 🔧 | - | In: text, image Out: text | Open Weights Released: 2025-09-22 Updated: 2026-01-19 |
OpenAI¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GPT-4o (2024-11-20) | gpt-4o-2024-11-20 | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-11-20 |
| GPT-5.3 Codex | gpt-5.3-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| GPT-5-Codex | gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| GPT-5 Pro | gpt-5-pro | 400K | 272K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-10-06 |
| GPT-4o mini | gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.08 | Model: 0.075 Completion: 4.000 Cache: 0.533 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-07-18 |
| TEXT-EMBEDDING-ADA-002 | text-embedding-ada-002 | 60K | 1.5K | Input: $6 Output: $12 Cache Read: $0.06 Cache Write: $0.45 | Model: 3.000 Completion: 2.000 Cache: 0.010 | 📎 🧠 🔧 🌡️ | 2023-10 | In: text Out: vector | Released: 2023-11-20 Updated: 2023-10-01 |
| GPT-5 Chat (latest) | gpt-5-chat-latest | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| Codex Mini | codex-mini-latest | 200K | 100K | Input: $1.5 Output: $6 Cache Read: $0.375 | Model: 0.750 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-04 | In: text Out: text | Released: 2025-05-16 |
| GPT-5.1 Codex Max | gpt-5.1-codex-max | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-4o (2024-05-13) | gpt-4o-2024-05-13 | 128K | 4.1K | Input: $5 Output: $15 | Model: 2.500 Completion: 3.000 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 |
| GPT-5.2 Chat | gpt-5.2-chat-latest | 128K | 16.4K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-5.2 Codex | gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image, pdf Out: text | Released: 2025-12-11 |
| o3-deep-research | o3-deep-research | 200K | 100K | Input: $10 Output: $40 Cache Read: $2.5 | Model: 5.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2024-06-26 |
| o1 | o1 | 200K | 100K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | 📎 🧠 🔧 | 2023-09 | In: text, image Out: text | Released: 2024-12-05 |
| GPT-5.1 | gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| o4-mini-deep-research | o4-mini-deep-research | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2024-06-26 |
| GPT-5.3 Codex Spark | gpt-5.3-codex-spark | 128K | 32K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| o3 | o3 | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| TEXT-EMBEDDING-3-SMALL | text-embedding-3-small | 32K | 1K | Input: $4 Output: $8 Cache Read: $0.04 Cache Write: $0.3 | Model: 2.000 Completion: 2.000 Cache: 0.010 | 📎 🧠 🔧 🌡️ | 2023-10 | In: text Out: vector | Released: 2023-11-10 Updated: 2023-10-01 |
| GPT-4.1 nano | gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 Cache Read: $0.03 | Model: 0.050 Completion: 4.000 Cache: 0.300 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| TEXT-EMBEDDING-3-LARGE | text-embedding-3-large | 64K | 2K | Input: $7 Output: $10 Cache Read: $0.05 Cache Write: $0.4 | Model: 3.500 Completion: 1.429 Cache: 0.007 | 📎 🧠 🔧 🌡️ | 2023-10 | In: text Out: vector | Released: 2023-12-15 Updated: 2023-10-01 |
| GPT-3.5-turbo | gpt-3.5-turbo | 16.4K | 4.1K | Input: $0.5 Output: $1.5 Cache Read: $1.25 | Model: 0.250 Completion: 3.000 Cache: 2.500 | 🌡️ | 2021-09-01 | In: text Out: text | Released: 2023-03-01 Updated: 2023-11-06 |
| GPT-5.1 Codex mini | gpt-5.1-codex-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-4.1 | gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| o3-pro | o3-pro | 200K | 100K | Input: $20 Output: $80 | Model: 10.000 Completion: 4.000 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-06-10 |
| GPT-4 Turbo | gpt-4-turbo | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| GPT-5 | gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| o4-mini | o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.28 | Model: 0.550 Completion: 4.000 Cache: 0.255 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-4.1 mini | gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| o1-preview | o1-preview | 128K | 32.8K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | 🧠 🌡️ | 2023-09 | In: text Out: text | Released: 2024-09-12 |
| o1-pro | o1-pro | 200K | 100K | Input: $150 Output: $600 | Model: 75.000 Completion: 4.000 | 📎 🧠 🔧 | 2023-09 | In: text, image Out: text | Released: 2025-03-19 |
| GPT-5.1 Codex | gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 Pro | gpt-5.2-pro | 400K | 128K | Input: $21 Output: $168 | Model: 10.500 Completion: 8.000 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| o3-mini | o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2024-05 | In: text Out: text | Released: 2024-12-20 Updated: 2025-01-29 |
| GPT-4o (2024-08-06) | gpt-4o-2024-08-06 | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-08-06 |
| GPT-5 Mini | gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-5.1 Chat | gpt-5.1-chat-latest | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-4 | gpt-4 | 8.2K | 8.2K | Input: $30 Output: $60 | Model: 15.000 Completion: 2.000 | 📎 🔧 🌡️ | 2023-11 | In: text Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| GPT-5 Nano | gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.005 | Model: 0.025 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| o1-mini | o1-mini | 128K | 65.5K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 | 2023-09 | In: text Out: text | Released: 2024-09-12 |
| GPT-4o | gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 Updated: 2024-08-06 |
| DALL-E 2 | dall-e-2 | 1K | 1 | Input: $0.02 Output: $0.1 Cache Read: $0.01 Cache Write: $0.05 | Model: 0.010 Completion: 5.000 Cache: 0.500 | 📎 🔧 | 2021-04 | In: text Out: image | Released: 2022-04-06 Updated: 2022-06-15 |
| DALL-E 3 | dall-e-3 | 2K | 1 | Input: $0.03 Output: $0.15 Cache Read: $0.01 Cache Write: $0.05 | Model: 0.015 Completion: 5.000 Cache: 0.333 | 📎 🔧 | 2024-04 | In: text Out: image | Released: 2024-03-01 Updated: 2024-08-15 |
| GPT-IMAGE-1 | gpt-image-1 | 1K | 512 | Input: $10 Output: $20 Cache Read: $0.1 Cache Write: $0.6 | Model: 5.000 Completion: 2.000 Cache: 0.010 | 📎 🧠 🔧 🌡️ | 2023-10 | In: text Out: image | Open Weights Released: 2024-01-15 Updated: 2024-10-01 |
OpenCode Zen¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.3 Codex | gpt-5.3-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-02-24 |
| Kimi K2 | kimi-k2 | 262.1K | 262.1K | Input: $0.4 Output: $2.5 Cache Read: $0.4 | Model: 0.200 Completion: 6.250 Cache: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| GPT-5 Codex | gpt-5-codex | 400K | 128K | Input: $1.07 Output: $8.5 Cache Read: $0.107 | Model: 0.535 Completion: 7.944 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| Gemini 3.1 Pro Preview | gemini-3.1-pro | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2026-02-19 |
| Trinity Large Preview | trinity-large-preview-free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-01-28 |
| GLM-5 | glm-5 | 204.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-02-11 |
| GPT-5.1 Codex Max | gpt-5.1-codex-max | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Kimi K2.5 Free | kimi-k2.5-free | 262.1K | 262.1K | Input: $0 Output: $0 Cache Read: $0 | - | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Claude Opus 4.1 | claude-opus-4-1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Grok Code Fast 1 | grok-code | 256K | 256K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 📎 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-20 |
| Claude Haiku 3.5 | claude-3-5-haiku | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| GPT-5.2 Codex | gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-01-14 |
| Claude Opus 4.6 | claude-opus-4-6 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08-31 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| Gemini 3 Flash | gemini-3-flash | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-12-17 |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| GPT-5.1 | gpt-5.1 | 400K | 128K | Input: $1.07 Output: $8.5 Cache Read: $0.107 | Model: 0.535 Completion: 7.944 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Qwen3 Coder | qwen3-coder | 262.1K | 65.5K | Input: $0.45 Output: $1.8 | Model: 0.225 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| GLM-4.6 | glm-4.6 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.1 | Model: 0.300 Completion: 3.667 Cache: 0.167 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| MiniMax M2.1 | minimax-m2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.1 | Model: 0.150 Completion: 4.000 Cache: 0.333 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-12-23 |
| GPT-5.1 Codex Mini | gpt-5.1-codex-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| Kimi K2.5 | kimi-k2.5 | 262.1K | 65.5K | Input: $0.6 Output: $3 Cache Read: $0.08 | Model: 0.300 Completion: 5.000 Cache: 0.133 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| MiniMax M2.1 Free | minimax-m2.1-free | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 | - | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-12-23 |
| GPT-5 | gpt-5 | 400K | 128K | Input: $1.07 Output: $8.5 Cache Read: $0.107 | Model: 0.535 Completion: 7.944 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| GLM-4.7 | glm-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.1 | Model: 0.300 Completion: 3.667 Cache: 0.167 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-5 Free | glm-5-free | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-02-11 |
| Kimi K2 Thinking | kimi-k2-thinking | 262.1K | 262.1K | Input: $0.4 Output: $2.5 Cache Read: $0.4 | Model: 0.200 Completion: 6.250 Cache: 1.000 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| GPT-5.1 Codex | gpt-5.1-codex | 400K | 128K | Input: $1.07 Output: $8.5 Cache Read: $0.107 | Model: 0.535 Completion: 7.944 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Big Pickle | big-pickle | 200K | 128K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Released: 2025-10-17 |
| MiniMax M2.5 Free | minimax-m2.5-free | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 | - | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2026-02-12 |
| MiniMax M2.5 | minimax-m2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.06 | Model: 0.150 Completion: 4.000 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2026-02-12 |
| Claude Opus 4.5 | claude-opus-4-5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Claude Sonnet 4 | claude-sonnet-4 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| GLM-4.7 Free | glm-4.7-free | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| Gemini 3 Pro | gemini-3-pro | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-11-18 |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| GPT-5 Nano | gpt-5-nano | 400K | 128K | Input: $0 Output: $0 Cache Read: $0 | - | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
OpenCode Go¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5 | glm-5 | 204.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-02-11 |
| Kimi K2.5 | kimi-k2.5 | 262.1K | 65.5K | Input: $0.6 Output: $3 Cache Read: $0.08 | Model: 0.300 Completion: 5.000 Cache: 0.133 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| MiniMax M2.5 | minimax-m2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.06 | Model: 0.150 Completion: 4.000 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2026-02-12 |
OpenRouter¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Intellect 3 | prime-intellect/intellect-3 | 131.1K | 8.2K | Input: $0.2 Output: $1.1 | Model: 0.100 Completion: 5.500 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-01-15 |
| Qwerky 72B | featherless/qwerky-72b | 32.8K | 8.2K | Input: $0 Output: $0 | - | 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-03-20 |
| Molmo2 8B (free) | allenai/molmo-2-8b:free | 36.9K | 36.9K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2025-06 | In: text, image, video Out: text | Open Weights Released: 2026-01-09 Updated: 2026-01-31 |
| Nemotron Nano 9B V2 (free) | nvidia/nemotron-nano-9b-v2:free | 128K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-09 | In: text Out: text | Open Weights Released: 2025-09-05 Updated: 2025-08-18 |
| Nemotron Nano 12B 2 VL (free) | nvidia/nemotron-nano-12b-v2-vl:free | 128K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-11 | In: text, image Out: text | Open Weights Released: 2025-10-28 Updated: 2026-01-31 |
| Nemotron 3 Nano 30B A3B (free) | nvidia/nemotron-3-nano-30b-a3b:free | 256K | 256K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2025-12-14 Updated: 2026-01-31 |
| nvidia-nemotron-nano-9b-v2 | nvidia/nemotron-nano-9b-v2 | 131.1K | 131.1K | Input: $0.04 Output: $0.16 | Model: 0.020 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-09 | In: text Out: text | Open Weights Released: 2025-08-18 |
| Trinity Large Preview | arcee-ai/trinity-large-preview:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-01-28 |
| Trinity Mini | arcee-ai/trinity-mini:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-01-28 |
| MiMo-V2-Flash | xiaomi/mimo-v2-flash | 262.1K | 65.5K | Input: $0.1 Output: $0.3 Cache Read: $0.01 | Model: 0.050 Completion: 3.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2025-12-14 |
| MAI DS R1 (free) | microsoft/mai-ds-r1:free | 163.8K | 163.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-21 |
| Sarvam-M (free) | sarvamai/sarvam-m:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-25 |
| LFM2.5-1.2B-Thinking (free) | liquid/lfm-2.5-1.2b-thinking:free | 131.1K | 32.8K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-01-20 Updated: 2026-01-28 |
| LFM2.5-1.2B-Instruct (free) | liquid/lfm-2.5-1.2b-instruct:free | 131.1K | 32.8K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2026-01-20 Updated: 2026-01-28 |
| GLM Z1 32B (free) | thudm/glm-z1-32b:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-17 |
| Riverflow V2 Fast Preview | sourceful/riverflow-v2-fast-preview | 8.2K | 8.2K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: text, image Out: image | Open Weights Released: 2025-12-08 Updated: 2026-01-28 |
| Riverflow V2 Max Preview | sourceful/riverflow-v2-max-preview | 8.2K | 8.2K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: text, image Out: image | Open Weights Released: 2025-12-08 Updated: 2026-01-28 |
| Riverflow V2 Standard Preview | sourceful/riverflow-v2-standard-preview | 8.2K | 8.2K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: text, image Out: image | Open Weights Released: 2025-12-08 Updated: 2026-01-28 |
| Reka Flash 3 | rekaai/reka-flash-3 | 32.8K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-03-12 |
| Step 3.5 Flash (free) | stepfun/step-3.5-flash:free | 256K | 256K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2026-01-29 |
| Step 3.5 Flash | stepfun/step-3.5-flash | 256K | 256K | Input: $0.1 Output: $0.3 Cache Read: $0.02 | Model: 0.050 Completion: 3.000 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2026-01-29 |
| Dolphin3.0 R1 Mistral 24B | cognitivecomputations/dolphin3.0-r1-mistral-24b | 32.8K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-02-13 |
| Dolphin3.0 Mistral 24B | cognitivecomputations/dolphin3.0-mistral-24b | 32.8K | 8.2K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-02-13 |
| Uncensored (free) | cognitivecomputations/dolphin-mistral-24b-venice-edition:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-07-09 Updated: 2026-01-31 |
| Kat Coder Pro (free) | kwaipilot/kat-coder-pro:free | 256K | 65.5K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-11 | In: text Out: text | Released: 2025-11-10 |
| DeepSeek V3.1 Terminus (exacto) | deepseek/deepseek-v3.1-terminus:exacto | 131.1K | 65.5K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-09-22 |
| R1 0528 (free) | deepseek/deepseek-r1-0528:free | 163.8K | 163.8K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek R1 Distill Qwen 14B | deepseek/deepseek-r1-distill-qwen-14b | 64K | 8.2K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-01-29 |
| R1 (free) | deepseek/deepseek-r1:free | 163.8K | 163.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-01-20 |
| Deepseek R1 0528 Qwen3 8B (free) | deepseek/deepseek-r1-0528-qwen3-8b:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-29 |
| DeepSeek V3.2 Speciale | deepseek/deepseek-v3.2-speciale | 163.8K | 65.5K | Input: $0.27 Output: $0.41 | Model: 0.135 Completion: 1.519 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| DeepSeek-V3.1 | deepseek/deepseek-chat-v3.1 | 163.8K | 163.8K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-08-21 |
| DeepSeek V3 0324 | deepseek/deepseek-chat-v3-0324 | 16.4K | 8.2K | Input: $0 Output: $0 | - | 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-03-24 |
| DeepSeek R1 Distill Llama 70B | deepseek/deepseek-r1-distill-llama-70b | 8.2K | 8.2K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-01-23 |
| DeepSeek V3.1 Terminus | deepseek/deepseek-v3.1-terminus | 131.1K | 65.5K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-09-22 |
| DeepSeek V3.2 | deepseek/deepseek-v3.2 | 163.8K | 65.5K | Input: $0.28 Output: $0.4 | Model: 0.140 Completion: 1.429 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| DeepSeek V3 Base (free) | deepseek/deepseek-v3-base:free | 163.8K | 163.8K | Input: $0 Output: $0 | - | 🌡️ | 2025-03 | In: text Out: text | Open Weights Released: 2025-03-29 |
| Sherlock Think Alpha | openrouter/sherlock-think-alpha | 1.8M | - | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-11 | In: text, image Out: text | Released: 2025-11-15 Updated: 2025-12-14 |
| Sherlock Dash Alpha | openrouter/sherlock-dash-alpha | 1.8M | - | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-11 | In: text, image Out: text | Released: 2025-11-15 Updated: 2025-12-14 |
| Aurora Alpha | openrouter/aurora-alpha | 128K | 50K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-09 |
| Kimi Dev 72b (free) | moonshotai/kimi-dev-72b:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-06-16 |
| Kimi K2 | moonshotai/kimi-k2 | 131.1K | 32.8K | Input: $0.55 Output: $2.2 | Model: 0.275 Completion: 4.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-11 |
| Kimi K2 Instruct 0905 | moonshotai/kimi-k2-0905 | 262.1K | 16.4K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2 Instruct 0905 (exacto) | moonshotai/kimi-k2-0905:exacto | 262.1K | 16.4K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2.5 | moonshotai/kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $3 Cache Read: $0.1 | Model: 0.300 Completion: 5.000 Cache: 0.167 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 262.1K | 262.1K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Kimi K2 (free) | moonshotai/kimi-k2:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-11 |
| Gemini 2.5 Flash Lite Preview 09-25 | google/gemini-2.5-flash-lite-preview-09-2025 | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Pro Preview 06-05 | google/gemini-2.5-pro-preview-06-05 | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-05 |
| Gemma 3n 4B (free) | google/gemma-3n-e4b-it:free | 8.2K | 2K | Input: $0 Output: $0 | - | 📎 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-05-20 |
| Gemini 2.5 Flash Preview 09-25 | google/gemini-2.5-flash-preview-09-2025 | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.031 | Model: 0.150 Completion: 8.333 Cache: 0.103 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 2.5 Pro Preview 05-06 | google/gemini-2.5-pro-preview-05-06 | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-05-06 |
| Gemma 3n 2B (free) | google/gemma-3n-e2b-it:free | 8.2K | 2K | Input: $0 Output: $0 | - | 📎 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-07-09 |
| Gemini 2.5 Flash | google/gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.0375 | Model: 0.150 Completion: 8.333 Cache: 0.125 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-07-17 |
| Gemini 2.0 Flash | google/gemini-2.0-flash-001 | 1M | 8.2K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-06 | In: text, image, audio, video, pdf Out: text | Released: 2024-12-11 |
| Gemini 3 Flash Preview | google/gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-12-17 |
| Gemma 3 12B (free) | google/gemma-3-12b-it:free | 32.8K | 8.2K | Input: $0 Output: $0 | - | 📎 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Gemini 2.5 Flash Lite | google/gemini-2.5-flash-lite | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 3.1 Pro Preview | google/gemini-3.1-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Reasoning: $12 | Model: 1.000 Completion: 6.000 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2026-02-19 |
| Gemini 2.0 Flash Experimental (free) | google/gemini-2.0-flash-exp:free | 1M | 1M | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-12 | In: text, image Out: text | Released: 2024-12-11 |
| Gemma 2 9B | google/gemma-2-9b-it | 8.2K | 8.2K | Input: $0.03 Output: $0.09 | Model: 0.015 Completion: 3.000 | 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2024-06-28 |
| Gemma 3 4B (free) | google/gemma-3-4b-it:free | 32.8K | 8.2K | Input: $0 Output: $0 | - | 📎 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Gemma 3n 4B | google/gemma-3n-e4b-it | 32.8K | 32.8K | Input: $0.02 Output: $0.04 | Model: 0.010 Completion: 2.000 | 📎 🌡️ | 2024-06 | In: text Out: text | Open Weights Released: 2025-05-20 |
| Gemini 3 Pro Preview | google/gemini-3-pro-preview | 1.1M | 66K | Input: $2 Output: $12 | Model: 1.000 Completion: 6.000 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-11-18 Updated: 2025-11 |
| Gemma 3 12B | google/gemma-3-12b-it | 131.1K | 131.1K | Input: $0.03 Output: $0.1 | Model: 0.015 Completion: 3.333 | 📎 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Gemma 3 4B | google/gemma-3-4b-it | 96K | 96K | Input: $0.01703 Output: $0.06815 | Model: 0.009 Completion: 4.002 | 📎 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-03-13 |
| Gemma 3 27B | google/gemma-3-27b-it | 96K | 96K | Input: $0.04 Output: $0.15 | Model: 0.020 Completion: 3.750 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-03-12 |
| Gemini 2.5 Pro | google/gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| Gemma 3 27B (free) | google/gemma-3-27b-it:free | 131.1K | 8.2K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-03-12 |
| GLM-5 | z-ai/glm-5 | 202.8K | 131K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| GLM 4.5 Air | z-ai/glm-4.5-air | 128K | 96K | Input: $0.2 Output: $1.1 | Model: 0.100 Completion: 5.500 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM 4.5 | z-ai/glm-4.5 | 128K | 96K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM 4.6 (exacto) | z-ai/glm-4.6:exacto | 200K | 128K | Input: $0.6 Output: $1.9 Cache Read: $0.11 | Model: 0.300 Completion: 3.167 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7-Flash | z-ai/glm-4.7-flash | 200K | 65.5K | Input: $0.07 Output: $0.4 | Model: 0.035 Completion: 5.714 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-19 |
| GLM 4.5 Air (free) | z-ai/glm-4.5-air:free | 128K | 96K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM 4.6 | z-ai/glm-4.6 | 200K | 128K | Input: $0.6 Output: $2.2 Cache Read: $0.11 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7 | z-ai/glm-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.11 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM 4.5V | z-ai/glm-4.5v | 64K | 16.4K | Input: $0.6 Output: $1.8 | Model: 0.300 Completion: 3.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-08-11 |
| Qwen3 Next 80B A3B Thinking | qwen/qwen3-next-80b-a3b-thinking | 262.1K | 262.1K | Input: $0.14 Output: $1.4 | Model: 0.070 Completion: 10.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen2.5-VL 7B Instruct (free) | qwen/qwen-2.5-vl-7b-instruct:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-02 | In: text, image Out: text | Open Weights Released: 2024-08-28 |
| Qwen3 32B (free) | qwen/qwen3-32b:free | 41K | 41K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 |
| Qwen3 Coder 480B A35B Instruct (free) | qwen/qwen3-coder:free | 262.1K | 66.5K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen3 Coder Flash | qwen/qwen3-coder-flash | 128K | 66.5K | Input: $0.3 Output: $1.5 | Model: 0.150 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-07-23 |
| Qwen3 30B A3B (free) | qwen/qwen3-30b-a3b:free | 41K | 41K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 |
| Qwen3 235B A22B Instruct 2507 (free) | qwen/qwen3-235b-a22b-07-25:free | 262.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 Updated: 2025-07-21 |
| Qwen3 14B (free) | qwen/qwen3-14b:free | 41K | 41K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 |
| Qwen3 Coder | qwen/qwen3-coder | 262.1K | 66.5K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| QwQ 32B (free) | qwen/qwq-32b:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-03 | In: text Out: text | Open Weights Released: 2025-03-05 |
| Qwen3.5 397B A17B | qwen/qwen3.5-397b-a17b | 262.1K | 65.5K | Input: $0.6 Output: $3.6 | Model: 0.300 Completion: 6.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2026-02-16 |
| Qwen3 Coder (exacto) | qwen/qwen3-coder:exacto | 131.1K | 32.8K | Input: $0.38 Output: $1.53 | Model: 0.190 Completion: 4.026 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen2.5 Coder 32B Instruct | qwen/qwen-2.5-coder-32b-instruct | 32.8K | 8.2K | Input: $0 Output: $0 | - | 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-11-11 |
| Qwen3.5 Plus 2026-02-15 | qwen/qwen3.5-plus-02-15 | 1M | 65.5K | Input: $0.4 Output: $2.4 | Model: 0.200 Completion: 6.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Released: 2026-02-16 |
| Qwen3 30B A3B Instruct 2507 | qwen/qwen3-30b-a3b-instruct-2507 | 262K | 262K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-29 |
| Qwen2.5 VL 72B Instruct | qwen/qwen2.5-vl-72b-instruct | 32.8K | 8.2K | Input: $0 Output: $0 | - | 📎 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-02-01 |
| Qwen3 Coder 30B A3B Instruct | qwen/qwen3-coder-30b-a3b-instruct | 160K | 65.5K | Input: $0.07 Output: $0.27 | Model: 0.035 Completion: 3.857 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-31 |
| Qwen3 235B A22B Instruct 2507 | qwen/qwen3-235b-a22b-07-25 | 262.1K | 131.1K | Input: $0.15 Output: $0.85 | Model: 0.075 Completion: 5.667 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 Updated: 2025-07-21 |
| Qwen3 235B A22B (free) | qwen/qwen3-235b-a22b:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 |
| Qwen3 Next 80B A3B Instruct (free) | qwen/qwen3-next-80b-a3b-instruct:free | 262.1K | 262.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen3 4B (free) | qwen/qwen3-4b:free | 41K | 41K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-30 Updated: 2025-07-23 |
| Qwen3 8B (free) | qwen/qwen3-8b:free | 41K | 41K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 |
| Qwen3 30B A3B Thinking 2507 | qwen/qwen3-30b-a3b-thinking-2507 | 262K | 262K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-29 |
| Qwen2.5 VL 32B Instruct (free) | qwen/qwen2.5-vl-32b-instruct:free | 8.2K | 8.2K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-03 | In: text, image, video Out: text | Open Weights Released: 2025-03-24 |
| Qwen3 235B A22B Thinking 2507 | qwen/qwen3-235b-a22b-thinking-2507 | 262.1K | 81.9K | Input: $0.078 Output: $0.312 | Model: 0.039 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen3 Next 80B A3B Instruct | qwen/qwen3-next-80b-a3b-instruct | 262.1K | 262.1K | Input: $0.14 Output: $1.4 | Model: 0.070 Completion: 10.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-11 |
| Qwen2.5 VL 72B Instruct (free) | qwen/qwen2.5-vl-72b-instruct:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-02 | In: text, image Out: text | Open Weights Released: 2025-02-01 |
| Qwen3 Max | qwen/qwen3-max | 262.1K | 32.8K | Input: $1.2 Output: $6 | Model: 0.600 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-05 |
| Grok 3 | x-ai/grok-3 | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 Cache Write: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok Code Fast 1 | x-ai/grok-code-fast-1 | 256K | 10K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-08 | In: text Out: text | Released: 2025-08-26 |
| Grok 4 Fast | x-ai/grok-4-fast | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 Cache Write: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text, image Out: text | Released: 2025-08-19 |
| Grok 4 | x-ai/grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 Cache Write: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-09 |
| Grok 4.1 Fast | x-ai/grok-4.1-fast | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 Cache Write: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text, image Out: text | Released: 2025-11-19 |
| Grok 3 Mini Beta | x-ai/grok-3-mini-beta | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 Cache Write: $0.5 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 3 Mini | x-ai/grok-3-mini | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 Cache Write: $0.5 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 3 Beta | x-ai/grok-3-beta | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 Cache Write: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Llama 3.3 70B Instruct (free) | meta-llama/llama-3.3-70b-instruct:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Llama 4 Scout (free) | meta-llama/llama-4-scout:free | 64K | 64K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Llama 3.2 11B Vision Instruct | meta-llama/llama-3.2-11b-vision-instruct | 131.1K | 8.2K | Input: $0 Output: $0 | - | 📎 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Llama 3.2 3B Instruct (free) | meta-llama/llama-3.2-3b-instruct:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 📎 🌡️ | 2023-12 | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Llama 3.1 405B Instruct (free) | meta-llama/llama-3.1-405b-instruct:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 📎 🌡️ | 2024-08 | In: text Out: text | Open Weights Released: 2024-07-23 Updated: 2025-04-05 |
| R1T Chimera (free) | tngtech/tng-r1t-chimera:free | 163.8K | 163.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-11-26 Updated: 2026-01-31 |
| DeepSeek R1T2 Chimera (free) | tngtech/deepseek-r1t2-chimera:free | 163.8K | 163.8K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-07-08 |
| Devstral Medium | mistralai/devstral-medium-2507 | 131.1K | 131.1K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-07-10 |
| Devstral Small 2505 (free) | mistralai/devstral-small-2505:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-21 |
| Mistral Medium 3 | mistralai/mistral-medium-3 | 131.1K | 131.1K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-05-07 |
| Codestral 2508 | mistralai/codestral-2508 | 256K | 256K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-08-01 |
| Devstral 2 2512 (free) | mistralai/devstral-2512:free | 262.1K | 262.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-09-12 |
| Mistral Small 3.1 24B Instruct | mistralai/mistral-small-3.1-24b-instruct | 128K | 8.2K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-03-17 |
| Devstral Small | mistralai/devstral-small-2505 | 128K | 128K | Input: $0.06 Output: $0.12 | Model: 0.030 Completion: 2.000 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-07 |
| Mistral 7B Instruct (free) | mistralai/mistral-7b-instruct:free | 32.8K | 32.8K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-05 | In: text Out: text | Open Weights Released: 2024-05-27 |
| Devstral 2 2512 | mistralai/devstral-2512 | 262.1K | 262.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🔧 🌡️ | 2025-12 | In: text Out: text | Open Weights Released: 2025-09-12 |
| Mistral Small 3.2 24B Instruct | mistralai/mistral-small-3.2-24b-instruct | 96K | 8.2K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Open Weights Released: 2025-06-20 |
| Mistral Small 3.2 24B (free) | mistralai/mistral-small-3.2-24b-instruct:free | 96K | 96K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2025-06 | In: text, image Out: text | Open Weights Released: 2025-06-20 |
| Devstral Small 1.1 | mistralai/devstral-small-2507 | 131.1K | 131.1K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-07-10 |
| Mistral Nemo (free) | mistralai/mistral-nemo:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2024-07-19 |
| Mistral Medium 3.1 | mistralai/mistral-medium-3.1 | 262.1K | 262.1K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | 2025-05 | In: text, image Out: text | Released: 2025-08-12 |
| GPT-5 Codex | openai/gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image Out: text | Released: 2025-09-15 |
| GPT-5 Pro | openai/gpt-5-pro | 400K | 272K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-10-06 |
| GPT-4o-mini | openai/gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.08 | Model: 0.075 Completion: 4.000 Cache: 0.533 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-07-18 |
| GPT-5.1-Codex-Max | openai/gpt-5.1-codex-max | 400K | 128K | Input: $1.1 Output: $9 Cache Read: $0.11 | Model: 0.550 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2-Codex | openai/gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08-31 | In: text, image Out: text | Released: 2026-01-14 |
| GPT OSS 120B (exacto) | openai/gpt-oss-120b:exacto | 131.1K | 32.8K | Input: $0.05 Output: $0.24 | Model: 0.025 Completion: 4.800 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT-5.1 | openai/gpt-5.1 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 Chat | openai/gpt-5.2-chat | 128K | 16.4K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-5 Chat (latest) | openai/gpt-5-chat | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-5.1 Chat | openai/gpt-5.1-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5 Image | openai/gpt-5-image | 400K | 128K | Input: $5 Output: $10 Cache Read: $1.25 | Model: 2.500 Completion: 2.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image, pdf Out: text, image | Released: 2025-10-14 |
| GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 32.8K | Input: $0.072 Output: $0.28 | Model: 0.036 Completion: 3.889 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT-5.1-Codex-Mini | openai/gpt-5.1-codex-mini | 400K | 100K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 | openai/gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| gpt-oss-20b (free) | openai/gpt-oss-20b:free | 131.1K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 Updated: 2026-01-31 |
| GPT-4.1 | openai/gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GPT-5 | openai/gpt-5 | 400K | 128K | Input: $1.25 Output: $10 | Model: 0.625 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image Out: text | Released: 2025-08-07 |
| o4 Mini | openai/o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.28 | Model: 0.550 Completion: 4.000 Cache: 0.255 | 📎 🧠 🔧 🌡️ | 2024-06 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-4.1 Mini | openai/gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GPT OSS Safeguard 20B | openai/gpt-oss-safeguard-20b | 131.1K | 65.5K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-29 |
| GPT-5.1-Codex | openai/gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 Pro | openai/gpt-5.2-pro | 400K | 128K | Input: $21 Output: $168 | Model: 10.500 Completion: 8.000 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| GPT-5 Mini | openai/gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 | Model: 0.125 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image Out: text | Released: 2025-08-07 |
| GPT OSS 20B | openai/gpt-oss-20b | 131.1K | 32.8K | Input: $0.05 Output: $0.2 | Model: 0.025 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| gpt-oss-120b (free) | openai/gpt-oss-120b:free | 131.1K | 32.8K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT-5 Nano | openai/gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 | Model: 0.025 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2024-10-01 | In: text, image Out: text | Released: 2025-08-07 |
| MiniMax M1 | minimax/minimax-m1 | 1M | 40K | Input: $0.4 Output: $2.2 | Model: 0.200 Completion: 5.500 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-17 |
| MiniMax-01 | minimax/minimax-01 | 1M | 1M | Input: $0.2 Output: $1.1 | Model: 0.100 Completion: 5.500 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-01-15 |
| MiniMax M2.1 | minimax/minimax-m2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| MiniMax M2 | minimax/minimax-m2 | 196.6K | 118K | Input: $0.28 Output: $1.15 Cache Read: $0.28 Cache Write: $1.15 | Model: 0.140 Completion: 4.107 Cache: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-23 |
| MiniMax M2.5 | minimax/minimax-m2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| Seedream 4.5 | bytedance-seed/seedream-4.5 | 4.1K | 4.1K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: image, text Out: image | Open Weights Released: 2025-12-23 Updated: 2026-01-31 |
| Claude Sonnet 3.7 | anthropic/claude-3.7-sonnet | 200K | 128K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-01 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Opus 4.1 | anthropic/claude-opus-4.1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude Sonnet 4.6 | anthropic/claude-sonnet-4.6 | 1M | 128K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-02-17 |
| Claude Haiku 4.5 | anthropic/claude-haiku-4.5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Haiku 3.5 | anthropic/claude-3.5-haiku | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Opus 4.5 | anthropic/claude-opus-4.5 | 200K | 32K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05-30 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Claude Opus 4 | anthropic/claude-opus-4 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 4 | anthropic/claude-sonnet-4 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 4.5 | anthropic/claude-sonnet-4.5 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Claude Opus 4.6 | anthropic/claude-opus-4.6 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05-30 | In: text, image, pdf Out: text | Released: 2026-02-05 |
| FLUX.2 Pro | black-forest-labs/flux.2-pro | 46.9K | 46.9K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: image, text Out: image | Released: 2025-11-25 Updated: 2026-01-31 |
| FLUX.2 Flex | black-forest-labs/flux.2-flex | 67.3K | 67.3K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: image, text Out: image | Released: 2025-11-25 Updated: 2026-01-31 |
| FLUX.2 Max | black-forest-labs/flux.2-max | 46.9K | 46.9K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: image, text Out: image | Released: 2025-12-16 Updated: 2026-01-31 |
| FLUX.2 Klein 4B | black-forest-labs/flux.2-klein-4b | 41K | 41K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: image, text Out: image | Open Weights Released: 2026-01-14 Updated: 2026-01-31 |
| Hermes 4 405B | nousresearch/hermes-4-405b | 131.1K | 131.1K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-08-25 |
| Hermes 4 70B | nousresearch/hermes-4-70b | 131.1K | 131.1K | Input: $0.13 Output: $0.4 | Model: 0.065 Completion: 3.077 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-08-25 |
| DeepHermes 3 Llama 3 8B Preview | nousresearch/deephermes-3-llama-3-8b-preview | 131.1K | 8.2K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2025-02-28 |
| Hermes 3 405B Instruct (free) | nousresearch/hermes-3-llama-3.1-405b:free | 131.1K | 131.1K | Input: $0 Output: $0 | - | 🧠 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-08-16 |
OVHcloud AI Endpoints¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Meta-Llama-3_3-70B-Instruct | meta-llama-3_3-70b-instruct | 131.1K | 131.1K | Input: $0.74 Output: $0.74 | Model: 0.370 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-01 |
| Mistral-7B-Instruct-v0.3 | mistral-7b-instruct-v0.3 | 65.5K | 65.5K | Input: $0.11 Output: $0.11 | Model: 0.055 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-01 |
| Mistral-Small-3.2-24B-Instruct-2506 | mistral-small-3.2-24b-instruct-2506 | 131.1K | 131.1K | Input: $0.1 Output: $0.31 | Model: 0.050 Completion: 3.100 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-07-16 |
| Qwen3-32B | qwen3-32b | 32.8K | 32.8K | Input: $0.09 Output: $0.25 | Model: 0.045 Completion: 2.778 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-16 |
| Qwen2.5-Coder-32B-Instruct | qwen2.5-coder-32b-instruct | 32.8K | 32.8K | Input: $0.96 Output: $0.96 | Model: 0.480 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-03-24 |
| gpt-oss-120b | gpt-oss-120b | 131.1K | 131.1K | Input: $0.09 Output: $0.47 | Model: 0.045 Completion: 5.222 | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-08-28 |
| DeepSeek-R1-Distill-Llama-70B | deepseek-r1-distill-llama-70b | 131.1K | 131.1K | Input: $0.74 Output: $0.74 | Model: 0.370 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-01-30 |
| Qwen2.5-VL-72B-Instruct | qwen2.5-vl-72b-instruct | 32.8K | 32.8K | Input: $1.01 Output: $1.01 | Model: 0.505 Completion: 1.000 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-03-31 |
| Qwen3-Coder-30B-A3B-Instruct | qwen3-coder-30b-a3b-instruct | 262.1K | 262.1K | Input: $0.07 Output: $0.26 | Model: 0.035 Completion: 3.714 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-28 |
| Llama-3.1-8B-Instruct | llama-3.1-8b-instruct | 131.1K | 131.1K | Input: $0.11 Output: $0.11 | Model: 0.055 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-06-11 |
| Mistral-Nemo-Instruct-2407 | mistral-nemo-instruct-2407 | 65.5K | 65.5K | Input: $0.14 Output: $0.14 | Model: 0.070 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-11-20 |
| gpt-oss-20b | gpt-oss-20b | 131.1K | 131.1K | Input: $0.05 Output: $0.18 | Model: 0.025 Completion: 3.600 | 🧠 🔧 | - | In: text Out: text | Open Weights Released: 2025-08-28 |
| Mixtral-8x7B-Instruct-v0.1 | mixtral-8x7b-instruct-v0.1 | 32.8K | 32.8K | Input: $0.7 Output: $0.7 | Model: 0.350 Completion: 1.000 | 🌡️ | - | In: text Out: text | Open Weights Released: 2025-04-01 |
Perplexity¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Sonar Reasoning Pro | sonar-reasoning-pro | 128K | 4.1K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 📎 🧠 🌡️ | 2025-09-01 | In: text, image Out: text | Released: 2024-01-01 Updated: 2025-09-01 |
| Sonar | sonar | 128K | 4.1K | Input: $1 Output: $1 | Model: 0.500 Completion: 1.000 | 🌡️ | 2025-09-01 | In: text Out: text | Released: 2024-01-01 Updated: 2025-09-01 |
| Perplexity Sonar Deep Research | sonar-deep-research | 128K | 32.8K | Input: $2 Output: $8 Reasoning: $3 | Model: 1.000 Completion: 4.000 | 🧠 | 2025-01 | In: text Out: text | Released: 2025-02-01 Updated: 2025-09-01 |
| Sonar Pro | sonar-pro | 200K | 8.2K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🌡️ | 2025-09-01 | In: text, image Out: text | Released: 2024-01-01 Updated: 2025-09-01 |
Poe¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| StableDiffusionXL | stabilityai/stablediffusionxl | 200 | - | - | - | 📎 🔧 | - | In: text, image Out: image | Released: 2023-07-09 |
| Ideogram-v2 | ideogramai/ideogram-v2 | 150 | - | - | - | 📎 🔧 | - | In: text, image Out: image | Released: 2024-08-21 |
| Ideogram | ideogramai/ideogram | 150 | - | - | - | 📎 🔧 | - | In: text, image Out: image | Released: 2024-04-03 |
| Ideogram-v2a-Turbo | ideogramai/ideogram-v2a-turbo | 150 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2025-02-27 |
| Ideogram-v2a | ideogramai/ideogram-v2a | 150 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2025-02-27 |
| glm-4.7-flash | novita/glm-4.7-flash | 200K | 65.5K | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2026-01-19 |
| glm-4.7-n | novita/glm-4.7-n | 205K | 131.1K | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-12-22 |
| GLM-4.6 | novita/glm-4.6 | - | - | - | - | 📎 🔧 | - | In: text Out: text | Released: 2025-09-30 |
| minimax-m2.1 | novita/minimax-m2.1 | 205K | 131.1K | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-12-26 |
| kimi-k2.5 | novita/kimi-k2.5 | 256K | 262.1K | - | - | 📎 🧠 🔧 | - | In: text, image, video Out: text | Released: 2026-01-27 |
| glm-4.7 | novita/glm-4.7 | 205K | 131.1K | - | - | 📎 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-22 |
| kimi-k2-thinking | novita/kimi-k2-thinking | 256K | - | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-11-07 |
| glm-4.6v | novita/glm-4.6v | 131K | 32.8K | - | - | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-12-09 |
| Lyria | google/lyria | - | - | - | - | 📎 🔧 | - | In: text Out: audio | Released: 2025-06-04 |
| Gemini-3-Flash | google/gemini-3-flash | 1M | 65.5K | Input: $0.4 Output: $2.4 Cache Read: $0.04 | Model: 0.200 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, video, audio Out: text | Released: 2025-10-07 |
| Imagen-3 | google/imagen-3 | 480 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2024-10-15 |
| Gemini-2.5-Flash | google/gemini-2.5-flash | 1.1M | 65.5K | Input: $0.21 Output: $1.8 Cache Read: $0.021 | Model: 0.105 Completion: 8.571 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, video, audio Out: text | Released: 2025-04-26 |
| Veo-3.1 | google/veo-3.1 | 480 | - | - | - | 📎 🔧 | - | In: text Out: video | Released: 2025-10-15 |
| Imagen-3-Fast | google/imagen-3-fast | 480 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2024-10-17 |
| Nano-Banana-Pro | google/nano-banana-pro | 65.5K | - | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🔧 | - | In: text, image Out: image | Released: 2025-11-19 |
| Veo-2 | google/veo-2 | 480 | - | - | - | 📎 🔧 | - | In: text Out: video | Released: 2024-12-02 |
| Imagen-4-Ultra | google/imagen-4-ultra | 480 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2025-05-24 |
| Gemini-2.5-Flash-Lite | google/gemini-2.5-flash-lite | 1M | 64K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 📎 🧠 🔧 | - | In: text, image, video, audio Out: text | Released: 2025-06-19 |
| Nano-Banana | google/nano-banana | 65.5K | - | Input: $0.21 Output: $1.8 Cache Read: $0.021 | Model: 0.105 Completion: 8.571 Cache: 0.100 | 📎 🔧 | - | In: text, image Out: text, image | Released: 2025-08-21 |
| Veo-3.1-Fast | google/veo-3.1-fast | 480 | - | - | - | 📎 🔧 | - | In: text, image Out: video | Released: 2025-10-15 |
| gemini-deep-research | google/gemini-deep-research | 1M | - | Input: $1.6 Output: $9.6 | Model: 0.800 Completion: 6.000 | 📎 🧠 🔧 | - | In: text, image, video Out: text | Released: 2025-12-11 |
| Veo-3 | google/veo-3 | 480 | - | - | - | 📎 🔧 | - | In: text Out: video | Released: 2025-05-21 |
| Imagen-4 | google/imagen-4 | 480 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2025-05-22 |
| Gemini-2.0-Flash-Lite | google/gemini-2.0-flash-lite | 990K | 8.2K | Input: $0.052 Output: $0.21 | Model: 0.026 Completion: 4.038 | 📎 🔧 | - | In: text, image, video, audio Out: text | Released: 2025-02-05 |
| Gemini-3-Pro | google/gemini-3-pro | 1M | 65.5K | Input: $1.6 Output: $9.6 Cache Read: $0.16 | Model: 0.800 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, video, audio Out: text | Released: 2025-10-22 |
| Gemini-2.5-Pro | google/gemini-2.5-pro | 1.1M | 65.5K | Input: $0.87 Output: $7 Cache Read: $0.087 | Model: 0.435 Completion: 8.046 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, video, audio Out: text | Released: 2025-02-05 |
| Gemini-2.0-Flash | google/gemini-2.0-flash | 990K | 8.2K | Input: $0.1 Output: $0.42 | Model: 0.050 Completion: 4.200 | 📎 🔧 | - | In: text, image, video, audio Out: text | Released: 2024-12-11 |
| Veo-3-Fast | google/veo-3-fast | 480 | - | - | - | 📎 🔧 | - | In: text Out: video | Released: 2025-10-13 |
| Imagen-4-Fast | google/imagen-4-fast | 480 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2025-06-25 |
| Ray2 | lumalabs/ray2 | 5K | - | - | - | 📎 🔧 | - | In: text, image Out: video | Released: 2025-02-20 |
| claude-code | poetools/claude-code | - | - | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-11-27 |
| GPT-5-Codex | openai/gpt-5-codex | 400K | 128K | Input: $1.1 Output: $9 | Model: 0.550 Completion: 8.182 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-09-23 |
| GPT-5-Pro | openai/gpt-5-pro | 400K | 128K | Input: $14 Output: $110 | Model: 7.000 Completion: 7.857 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-10-06 |
| GPT-4o-mini | openai/gpt-4o-mini | 128K | 4.1K | Input: $0.14 Output: $0.54 Cache Read: $0.068 | Model: 0.070 Completion: 3.857 Cache: 0.486 | 📎 🔧 | - | In: text, image Out: text | Released: 2024-07-18 |
| GPT-5.1-Codex-Max | openai/gpt-5.1-codex-max | 400K | 128K | Input: $1.1 Output: $9 Cache Read: $0.11 | Model: 0.550 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-12-08 |
| GPT-5.2-Codex | openai/gpt-5.2-codex | 400K | 128K | Input: $1.6 Output: $13 Cache Read: $0.16 | Model: 0.800 Completion: 8.125 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2026-01-14 |
| o3-deep-research | openai/o3-deep-research | 200K | 100K | Input: $9 Output: $36 Cache Read: $2.2 | Model: 4.500 Completion: 4.000 Cache: 0.244 | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-06-27 |
| o1 | openai/o1 | 200K | 100K | Input: $14 Output: $54 | Model: 7.000 Completion: 3.857 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2024-12-18 |
| GPT-5.1 | openai/gpt-5.1 | 400K | 128K | Input: $1.1 Output: $9 Cache Read: $0.11 | Model: 0.550 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-11-12 |
| o4-mini-deep-research | openai/o4-mini-deep-research | 200K | 100K | Input: $1.8 Output: $7.2 Cache Read: $0.45 | Model: 0.900 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-06-27 |
| GPT-5-Chat | openai/gpt-5-chat | 128K | 16.4K | Input: $1.1 Output: $9 Cache Read: $0.11 | Model: 0.550 Completion: 8.182 Cache: 0.100 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-08-07 |
| o3 | openai/o3 | 200K | 100K | Input: $1.8 Output: $7.2 Cache Read: $0.45 | Model: 0.900 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-04-16 |
| GPT-4-Classic | openai/gpt-4-classic | 8.2K | 4.1K | Input: $27 Output: $54 | Model: 13.500 Completion: 2.000 | 📎 🔧 | - | In: text, image Out: text | Released: 2024-03-25 |
| gpt-image-1.5 | openai/gpt-image-1.5 | 128K | - | - | - | 📎 🔧 | - | In: text, image Out: image | Released: 2025-12-16 |
| GPT-4.1-nano | openai/gpt-4.1-nano | 1M | 32.8K | Input: $0.09 Output: $0.36 Cache Read: $0.022 | Model: 0.045 Completion: 4.000 Cache: 0.244 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-04-15 |
| GPT-Image-1-Mini | openai/gpt-image-1-mini | - | - | - | - | 📎 🔧 | - | In: text, image Out: image | Released: 2025-08-26 |
| Sora-2-Pro | openai/sora-2-pro | - | - | - | - | 📎 🔧 | - | In: text, image Out: video | Released: 2025-10-06 |
| GPT-3.5-Turbo | openai/gpt-3.5-turbo | 16.4K | 2K | Input: $0.45 Output: $1.4 | Model: 0.225 Completion: 3.111 | 📎 🔧 | - | In: text, image Out: text | Released: 2023-09-13 |
| GPT-5.1-Codex-Mini | openai/gpt-5.1-codex-mini | 400K | 128K | Input: $0.22 Output: $1.8 Cache Read: $0.022 | Model: 0.110 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-11-12 |
| GPT-5.2 | openai/gpt-5.2 | 400K | 128K | Input: $1.6 Output: $13 Cache Read: $0.16 | Model: 0.800 Completion: 8.125 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-12-08 |
| GPT-4.1 | openai/gpt-4.1 | 1M | 32.8K | Input: $1.8 Output: $7.2 Cache Read: $0.45 | Model: 0.900 Completion: 4.000 Cache: 0.250 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-04-14 |
| GPT-4o-Aug | openai/gpt-4o-aug | 128K | 8.2K | Input: $2.2 Output: $9 Cache Read: $1.1 | Model: 1.100 Completion: 4.091 Cache: 0.500 | 📎 🔧 | - | In: text, image Out: text | Released: 2024-11-21 |
| o3-pro | openai/o3-pro | 200K | 100K | Input: $18 Output: $72 | Model: 9.000 Completion: 4.000 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-06-10 |
| GPT-4-Turbo | openai/gpt-4-turbo | 128K | 4.1K | Input: $9 Output: $27 | Model: 4.500 Completion: 3.000 | 📎 🔧 | - | In: text, image Out: text | Released: 2023-09-13 |
| GPT-Image-1 | openai/gpt-image-1 | 128K | - | - | - | 📎 🔧 | - | In: text, image Out: image | Released: 2025-03-31 |
| Sora-2 | openai/sora-2 | - | - | - | - | 📎 🔧 | - | In: text, image Out: video | Released: 2025-10-06 |
| GPT-3.5-Turbo-Raw | openai/gpt-3.5-turbo-raw | 4.5K | 2K | Input: $0.45 Output: $1.4 | Model: 0.225 Completion: 3.111 | 📎 🔧 | - | In: text, image Out: text | Released: 2023-09-27 |
| GPT-4o-mini-Search | openai/gpt-4o-mini-search | 128K | 8.2K | Input: $0.14 Output: $0.54 | Model: 0.070 Completion: 3.857 | 📎 🔧 | - | In: text Out: text | Released: 2025-03-11 |
| GPT-5 | openai/gpt-5 | 400K | 128K | Input: $1.1 Output: $9 Cache Read: $0.11 | Model: 0.550 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-08-05 |
| o4-mini | openai/o4-mini | 200K | 100K | Input: $0.99 Output: $4 Cache Read: $0.25 | Model: 0.495 Completion: 4.040 Cache: 0.253 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-04-16 |
| GPT-4.1-mini | openai/gpt-4.1-mini | 1M | 32.8K | Input: $0.36 Output: $1.4 Cache Read: $0.09 | Model: 0.180 Completion: 3.889 Cache: 0.250 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-04-15 |
| o1-pro | openai/o1-pro | 200K | 100K | Input: $140 Output: $540 | Model: 70.000 Completion: 3.857 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-03-19 |
| GPT-5.1-Codex | openai/gpt-5.1-codex | 400K | 128K | Input: $1.1 Output: $9 Cache Read: $0.11 | Model: 0.550 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-11-12 |
| ChatGPT-4o-Latest | openai/chatgpt-4o-latest | 128K | 8.2K | Input: $4.5 Output: $14 | Model: 2.250 Completion: 3.111 | 📎 🔧 | - | In: text, image Out: text | Released: 2024-08-14 |
| GPT-5.2-Pro | openai/gpt-5.2-pro | 400K | 128K | Input: $19 Output: $150 | Model: 9.500 Completion: 7.895 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-12-11 |
| DALL-E-3 | openai/dall-e-3 | 800 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2023-11-06 |
| o3-mini | openai/o3-mini | 200K | 100K | Input: $0.99 Output: $4 | Model: 0.495 Completion: 4.040 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-01-31 |
| GPT-4o-Search | openai/gpt-4o-search | 128K | 8.2K | Input: $2.2 Output: $9 | Model: 1.100 Completion: 4.091 | 📎 🔧 | - | In: text Out: text | Released: 2025-03-11 |
| GPT-5-mini | openai/gpt-5-mini | 400K | 128K | Input: $0.22 Output: $1.8 Cache Read: $0.022 | Model: 0.110 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-06-25 |
| GPT-4-Classic-0314 | openai/gpt-4-classic-0314 | 8.2K | 4.1K | Input: $27 Output: $54 | Model: 13.500 Completion: 2.000 | 📎 🔧 | - | In: text, image Out: text | Released: 2024-08-26 |
| GPT-5-nano | openai/gpt-5-nano | 400K | 128K | Input: $0.045 Output: $0.36 Cache Read: $0.0045 | Model: 0.022 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-08-05 |
| GPT-3.5-Turbo-Instruct | openai/gpt-3.5-turbo-instruct | 3.5K | 1K | Input: $1.4 Output: $1.8 | Model: 0.700 Completion: 1.286 | 📎 🔧 | - | In: text, image Out: text | Released: 2023-09-20 |
| GPT-5.2-Instant | openai/gpt-5.2-instant | 128K | 16.4K | Input: $1.6 Output: $13 Cache Read: $0.16 | Model: 0.800 Completion: 8.125 Cache: 0.100 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-12-11 |
| o3-mini-high | openai/o3-mini-high | 200K | 100K | Input: $0.99 Output: $4 | Model: 0.495 Completion: 4.040 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-01-31 |
| GPT-4o | openai/gpt-4o | 128K | 8.2K | - | - | 📎 🔧 | - | In: text, image Out: text | Released: 2024-05-13 |
| GPT-5.1-Instant | openai/gpt-5.1-instant | 128K | 16.4K | Input: $1.1 Output: $9 Cache Read: $0.11 | Model: 0.550 Completion: 8.182 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-11-12 |
| TopazLabs | topazlabs-co/topazlabs | 204 | - | - | - | 📎 🔧 | - | In: text Out: image | Released: 2024-12-03 |
| Runway | runwayml/runway | 256 | - | - | - | 📎 🔧 | - | In: text, image Out: video | Released: 2024-10-11 |
| Runway-Gen-4-Turbo | runwayml/runway-gen-4-turbo | 256 | - | - | - | 📎 🔧 | - | In: text, image Out: video | Released: 2025-05-09 |
| Claude-Sonnet-3.5-June | anthropic/claude-sonnet-3.5-june | 189.1K | 8.2K | Input: $2.6 Output: $13 Cache Read: $0.26 Cache Write: $3.2 | Model: 1.300 Completion: 5.000 Cache: 0.100 | 📎 🔧 | - | In: text, image, pdf Out: text | Released: 2024-11-18 |
| Claude-Opus-4.1 | anthropic/claude-opus-4.1 | 196.6K | 32K | Input: $13 Output: $64 Cache Read: $1.3 Cache Write: $16 | Model: 6.500 Completion: 4.923 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude-Sonnet-3.5 | anthropic/claude-sonnet-3.5 | 189.1K | 8.2K | Input: $2.6 Output: $13 Cache Read: $0.26 Cache Write: $3.2 | Model: 1.300 Completion: 5.000 Cache: 0.100 | 📎 🔧 | - | In: text, image, pdf Out: text | Released: 2024-06-05 |
| Claude-Haiku-3 | anthropic/claude-haiku-3 | 189.1K | 8.2K | Input: $0.21 Output: $1.1 Cache Read: $0.021 Cache Write: $0.26 | Model: 0.105 Completion: 5.238 Cache: 0.100 | 📎 🔧 | - | In: text, image, pdf Out: text | Released: 2024-03-09 |
| Claude-Haiku-3.5 | anthropic/claude-haiku-3.5 | 189.1K | 8.2K | Input: $0.68 Output: $3.4 Cache Read: $0.068 Cache Write: $0.85 | Model: 0.340 Completion: 5.000 Cache: 0.100 | 📎 🔧 | - | In: text, image, pdf Out: text | Released: 2024-10-01 |
| Claude-Sonnet-4.6 | anthropic/claude-sonnet-4.6 | 983K | 128K | Input: $2.6 Output: $13 Cache Read: $0.26 Cache Write: $3.2 | Model: 1.300 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, pdf Out: text | Released: 2026-02-05 |
| Claude-Haiku-4.5 | anthropic/claude-haiku-4.5 | 192K | 64K | Input: $0.85 Output: $4.3 Cache Read: $0.085 Cache Write: $1.1 | Model: 0.425 Completion: 5.059 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude-Opus-4.5 | anthropic/claude-opus-4.5 | 196.6K | 64K | Input: $4.3 Output: $21 Cache Read: $0.43 Cache Write: $5.3 | Model: 2.150 Completion: 4.884 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2025-11-21 |
| Claude-Opus-4 | anthropic/claude-opus-4 | 192.5K | 28.7K | Input: $13 Output: $64 Cache Read: $1.3 Cache Write: $16 | Model: 6.500 Completion: 4.923 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2025-05-21 |
| Claude-Sonnet-4 | anthropic/claude-sonnet-4 | 983K | 64K | Input: $2.6 Output: $13 Cache Read: $0.26 Cache Write: $3.2 | Model: 1.300 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2025-05-21 |
| Claude-Sonnet-4.5 | anthropic/claude-sonnet-4.5 | 983K | 32.8K | Input: $2.6 Output: $13 Cache Read: $0.26 Cache Write: $3.2 | Model: 1.300 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2025-09-26 |
| Claude-Opus-4.6 | anthropic/claude-opus-4.6 | 983K | 128K | Input: $4.3 Output: $21 Cache Read: $0.43 Cache Write: $5.3 | Model: 2.150 Completion: 4.884 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2026-02-04 |
| Claude-Sonnet-3.7 | anthropic/claude-sonnet-3.7 | 196.6K | 128K | Input: $2.6 Output: $13 Cache Read: $0.26 Cache Write: $3.2 | Model: 1.300 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 | - | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Tako | trytako/tako | 2K | - | - | - | 📎 🔧 | - | In: text Out: text | Released: 2024-08-15 |
| ElevenLabs-Music | elevenlabs/elevenlabs-music | 2K | - | - | - | 📎 🔧 | - | In: text Out: audio | Released: 2025-08-29 |
| ElevenLabs-v3 | elevenlabs/elevenlabs-v3 | 128K | - | - | - | 📎 🔧 | - | In: text Out: audio | Released: 2025-06-05 |
| ElevenLabs-v2.5-Turbo | elevenlabs/elevenlabs-v2.5-turbo | 128K | - | - | - | 📎 🔧 | - | In: text Out: audio | Released: 2024-10-28 |
| llama-3.1-8b-cs | cerebras/llama-3.1-8b-cs | - | - | - | - | 📎 🔧 | - | In: text Out: text | Released: 2025-05-13 |
| gpt-oss-120b-cs | cerebras/gpt-oss-120b-cs | - | - | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-08-06 |
| qwen3-235b-2507-cs | cerebras/qwen3-235b-2507-cs | - | - | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-08-06 |
| llama-3.3-70b-cs | cerebras/llama-3.3-70b-cs | - | - | - | - | 📎 | - | In: text Out: text | Released: 2025-05-13 |
| qwen3-32b-cs | cerebras/qwen3-32b-cs | - | - | - | - | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-05-15 |
| Grok-4-Fast-Reasoning | xai/grok-4-fast-reasoning | 2M | 128K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-09-16 |
| Grok 3 | xai/grok-3 | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 📎 🔧 | - | In: text Out: text | Released: 2025-04-11 |
| Grok Code Fast 1 | xai/grok-code-fast-1 | 256K | 128K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-08-22 |
| Grok-4.1-Fast-Reasoning | xai/grok-4.1-fast-reasoning | 2M | 30K | - | - | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-11-19 |
| Grok-4 | xai/grok-4 | 256K | 128K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 📎 🧠 🔧 | - | In: text, image Out: text | Released: 2025-07-10 |
| Grok-4.1-Fast-Non-Reasoning | xai/grok-4.1-fast-non-reasoning | 2M | 30K | - | - | 📎 🔧 | - | In: text, image Out: text | Released: 2025-11-19 |
| Grok 3 Mini | xai/grok-3-mini | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 📎 🧠 🔧 | - | In: text Out: text | Released: 2025-04-11 |
| Grok-4-Fast-Non-Reasoning | xai/grok-4-fast-non-reasoning | 2M | 128K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🔧 | - | In: text, image Out: text | Released: 2025-09-16 |
Privatemode AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 3 27B | gemma-3-27b | 128K | 8.2K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-03-12 |
| gpt-oss-120b | gpt-oss-120b | 128K | 128K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-08 | In: text Out: text | Open Weights Released: 2025-08-04 Updated: 2025-08-14 |
| Whisper large-v3 | whisper-large-v3 | - | 4.1K | Input: $0 Output: $0 | - | 📎 🌡️ | 2023-09 | In: audio Out: text | Open Weights Released: 2023-09-01 |
| Qwen3-Embedding 4B | qwen3-embedding-4b | 32K | 2.6K | Input: $0 Output: $0 | - | 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-06-06 |
| Qwen3-Coder 30B-A3B | qwen3-coder-30b-a3b | 128K | 32.8K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
QiHang¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.5 | claude-opus-4-5-20251101 | 200K | 32K | Input: $0.71 Output: $3.57 | Model: 0.355 Completion: 5.028 | 📎 🧠 🔧 🌡️ | 2025-03 | In: text, image Out: text | Released: 2025-11-01 |
| GPT-5.2 Codex | gpt-5.2-codex | 400K | 128K | Input: $0.14 Output: $1.14 | Model: 0.070 Completion: 8.143 | 📎 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.09 Output: $0.71 | Model: 0.045 Completion: 7.889 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-12-17 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.07 Output: $0.43 | Model: 0.035 Completion: 6.143 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-12-17 |
| Claude Sonnet 4.5 | claude-sonnet-4-5-20250929 | 200K | 64K | Input: $0.43 Output: $2.14 | Model: 0.215 Completion: 4.977 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| GPT-5.2 | gpt-5.2 | 400K | 128K | Input: $0.25 Output: $2 | Model: 0.125 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2025-08-31 | In: text, image Out: text | Released: 2025-12-11 |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 200K | 64K | Input: $0.14 Output: $0.71 | Model: 0.070 Completion: 5.071 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-10-01 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 65K | Input: $0.57 Output: $3.43 | Model: 0.285 Completion: 6.018 | 📎 🧠 🔧 🌡️ | 2025-11 | In: text, image, audio, video Out: text | Released: 2025-11-19 |
| GPT-5-Mini | gpt-5-mini | 200K | 64K | Input: $0.04 Output: $0.29 | Model: 0.020 Completion: 7.250 | 📎 🧠 🔧 🌡️ | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
Qiniu¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Claude 4.5 Haiku | claude-4.5-haiku | 200K | 64K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-16 |
| Claude 3.5 Sonnet | claude-3.5-sonnet | 200K | 8.2K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-09-09 |
| Qwen3 235b A22B Instruct 2507 | qwen3-235b-a22b-instruct-2507 | 262.1K | 64K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-12 |
| Kimi K2 | kimi-k2 | 128K | 128K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Claude 3.7 Sonnet | claude-3.7-sonnet | 200K | 128K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-05 |
| Qwen3 Max Preview | qwen3-max-preview | 256K | 64K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-06 |
| Qwen3 Next 80B A3B Thinking | qwen3-next-80b-a3b-thinking | 131.1K | 32.8K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-12 |
| Claude 4.0 Sonnet | claude-4.0-sonnet | 200K | 64K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-05 |
| Qwen VL-MAX-2025-01-25 | qwen-vl-max-2025-01-25 | 128K | 4.1K | - | - | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-08-05 |
| DeepSeek-V3 | deepseek-v3 | 128K | 16K | - | - | 🌡️ | - | In: text Out: text | Released: 2025-08-13 |
| Doubao-Seed 1.6 Thinking | doubao-seed-1.6-thinking | 256K | 32K | - | - | 📎 🧠 🔧 🌡️ | - | In: image, text, video Out: text | Released: 2025-08-15 |
| Qwen3 Coder 480B A35B Instruct | qwen3-coder-480b-a35b-instruct | 262K | 4.1K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-14 |
| Mimo-V2-Flash | mimo-v2-flash | 256K | 256K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-17 |
| GLM 4.5 Air | glm-4.5-air | 131K | 4.1K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| GLM 4.5 | glm-4.5 | 131.1K | 98.3K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Claude 4.5 Sonnet | claude-4.5-sonnet | 200K | 64K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-09-30 |
| Qwen 2.5 VL 7B Instruct | qwen2.5-vl-7b-instruct | 128K | 8.2K | - | - | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-08-05 |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | 64K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-08-05 |
| DeepSeek-V3.1 | deepseek-v3.1 | 128K | 32K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-19 |
| Doubao-Seed 1.6 | doubao-seed-1.6 | 256K | 32K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2025-08-15 |
| Claude 4.0 Opus | claude-4.0-opus | 200K | 32K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-05 |
| Qwen-Turbo | qwen-turbo | 1M | 4.1K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Gemini 3.0 Pro Preview | gemini-3.0-pro-preview | 1M | 64K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, video, pdf, audio Out: text | Released: 2025-11-19 |
| DeepSeek-R1-0528 | deepseek-r1-0528 | 128K | 32K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| DeepSeek-R1 | deepseek-r1 | 128K | 32K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Qwen3 32B | qwen3-32b | 40K | 4.1K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Doubao 1.5 Vision Pro | doubao-1.5-vision-pro | 128K | 16K | - | - | 📎 🌡️ | - | In: text, image, video Out: text | Released: 2025-08-05 |
| Gemini 3.0 Pro Image Preview | gemini-3.0-pro-image-preview | 32.8K | 8.2K | - | - | 📎 🌡️ | - | In: text, image Out: text, image | Released: 2025-11-20 |
| Gemini 2.5 Flash Lite | gemini-2.5-flash-lite | 1M | 64K | - | - | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-08-05 |
| Claude 3.5 Haiku | claude-3.5-haiku | 200K | 8.2K | - | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-26 |
| gpt-oss-120b | gpt-oss-120b | 128K | 4.1K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-06 |
| DeepSeek-V3-0324 | deepseek-v3-0324 | 128K | 16K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Doubao 1.5 Pro 32k | doubao-1.5-pro-32k | 128K | 12K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Qwen 2.5 VL 72B Instruct | qwen2.5-vl-72b-instruct | 128K | 8.2K | - | - | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-08-05 |
| Qwen 3 235B A22B | qwen3-235b-a22b | 128K | 32K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Claude 4.1 Opus | claude-4.1-opus | 200K | 32K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-06 |
| Doubao 1.5 Thinking Pro | doubao-1.5-thinking-pro | 128K | 16K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Gemini 2.5 Flash Image | gemini-2.5-flash-image | 32.8K | 8.2K | - | - | 📎 🌡️ | - | In: text, image Out: image | Released: 2025-10-22 |
| MiniMax M1 | MiniMax-M1 | 1M | 80K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| Doubao-Seed 1.6 Flash | doubao-seed-1.6-flash | 256K | 32K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, video Out: text | Released: 2025-08-15 |
| Claude 4.5 Opus | claude-4.5-opus | 200K | 200K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-11-25 |
| Qwen3 235B A22B Thinking 2507 | qwen3-235b-a22b-thinking-2507 | 262.1K | 4.1K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-12 |
| Gemini 2.0 Flash Lite | gemini-2.0-flash-lite | 1M | 8.2K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-08-05 |
| Qwen3 Next 80B A3B Instruct | qwen3-next-80b-a3b-instruct | 131.1K | 32.8K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-12 |
| Gemini 3.0 Flash Preview | gemini-3.0-flash-preview | 1M | 64K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video, pdf Out: text | Released: 2025-12-18 |
| Qwen3 Max | qwen3-max | 262.1K | 65.5K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-24 |
| Qwen3 30B A3B | qwen3-30b-a3b | 40K | 4.1K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| gpt-oss-20b | gpt-oss-20b | 128K | 4.1K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-06 |
| Kling-V2 6 | kling-v2-6 | 100M | 100M | - | - | 📎 🌡️ | - | In: text, image, video Out: video | Released: 2026-01-13 |
| Gemini 2.5 Pro | gemini-2.5-pro | 1M | 65.5K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, video, audio Out: text | Released: 2025-08-05 |
| Gemini 2.0 Flash | gemini-2.0-flash | 1M | 8.2K | - | - | 📎 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-08-05 |
| Qwen2.5-Max-2025-01-25 | qwen-max-2025-01-25 | 128K | 4.1K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-05 |
| DeepSeek/DeepSeek-V3.2-Exp-Thinking | deepseek/deepseek-v3.2-exp-thinking | 128K | 32K | - | - | 🧠 🌡️ | - | In: text Out: text | Released: 2025-09-29 |
| DeepSeek/DeepSeek-V3.1-Terminus | deepseek/deepseek-v3.1-terminus | 128K | 32K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-22 |
| Deepseek/DeepSeek-V3.2 | deepseek/deepseek-v3.2-251201 | 128K | 32K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-01 |
| Deepseek/Deepseek-Math-V2 | deepseek/deepseek-math-v2 | 160K | 160K | - | - | 🧠 🌡️ | - | In: text Out: text | Released: 2025-12-04 |
| DeepSeek/DeepSeek-V3.2-Exp | deepseek/deepseek-v3.2-exp | 128K | 32K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-29 |
| DeepSeek/DeepSeek-V3.1-Terminus-Thinking | deepseek/deepseek-v3.1-terminus-thinking | 128K | 32K | - | - | 🧠 🌡️ | - | In: text Out: text | Released: 2025-09-22 |
| Kimi K2 0905 | moonshotai/kimi-k2-0905 | 256K | 100K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-08 |
| Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 256K | 100K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-11-07 |
| Z-Ai/Autoglm Phone 9b | z-ai/autoglm-phone-9b | 12.8K | 4.1K | - | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-12-23 |
| Z-AI/GLM 4.6 | z-ai/glm-4.6 | 200K | 200K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-11 |
| Z-Ai/GLM 4.7 | z-ai/glm-4.7 | 200K | 200K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-23 |
| Stepfun-Ai/Gelab Zero 4b Preview | stepfun-ai/gelab-zero-4b-preview | 8.2K | 4.1K | - | - | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-12-23 |
| Meituan/Longcat-Flash-Chat | meituan/longcat-flash-chat | 131.1K | 131.1K | - | - | 🌡️ | - | In: text Out: text | Released: 2025-11-05 |
| X-Ai/Grok-4-Fast-Reasoning | x-ai/grok-4-fast-reasoning | 2M | 2M | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-12-18 |
| x-AI/Grok-Code-Fast 1 | x-ai/grok-code-fast-1 | 256K | 10K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-02 |
| X-Ai/Grok 4.1 Fast Reasoning | x-ai/grok-4.1-fast-reasoning | 20M | 2M | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-12-19 |
| x-AI/Grok-4-Fast | x-ai/grok-4-fast | 2M | 2M | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-09-20 |
| X-Ai/Grok 4.1 Fast Non Reasoning | x-ai/grok-4.1-fast-non-reasoning | 2M | 2M | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-12-19 |
| x-AI/Grok-4.1-Fast | x-ai/grok-4.1-fast | 2M | 2M | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-11-20 |
| X-Ai/Grok-4-Fast-Non-Reasoning | x-ai/grok-4-fast-non-reasoning | 2M | 2M | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2025-12-18 |
| OpenAI/GPT-5.2 | openai/gpt-5.2 | 400K | 128K | - | - | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-12-11 |
| OpenAI/GPT-5 | openai/gpt-5 | 400K | 128K | - | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-19 |
| Minimax/Minimax-M2.1 | minimax/minimax-m2.1 | 204.8K | 128K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-23 |
| Minimax/Minimax-M2 | minimax/minimax-m2 | 200K | 128K | - | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-28 |
Requesty¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 2.5 Flash | google/gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Cache Write: $0.55 | Model: 0.150 Completion: 8.333 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 3 Flash | google/gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 Cache Write: $1 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-12-17 |
| Gemini 3 Pro | google/gemini-3-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 Cache Write: $4.5 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-11-18 |
| Gemini 2.5 Pro | google/gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 Cache Write: $2.375 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| GPT-4o Mini | openai/gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.08 | Model: 0.075 Completion: 4.000 Cache: 0.533 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-07-18 |
| GPT-4.1 | openai/gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GPT-5 | openai/gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-09-30 | In: text, audio, image, video Out: text, audio, image | Released: 2025-08-07 |
| o4 Mini | openai/o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.28 | Model: 0.550 Completion: 4.000 Cache: 0.255 | 📎 🧠 🔧 🌡️ | 2024-06 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-4.1 Mini | openai/gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GPT-5 Mini | openai/gpt-5-mini | 128K | 32K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-5 Nano | openai/gpt-5-nano | 16K | 4K | Input: $0.05 Output: $0.4 Cache Read: $0.01 | Model: 0.025 Completion: 8.000 Cache: 0.200 | 📎 🧠 🔧 | 2024-05-30 | In: text Out: text | Released: 2025-08-07 |
| Claude Sonnet 3.7 | anthropic/claude-3-7-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-01 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Opus 4.1 | anthropic/claude-opus-4-1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-08-05 |
| Claude Opus 4 | anthropic/claude-opus-4 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Haiku 4.5 | anthropic/claude-haiku-4-5 | 200K | 62K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-01 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Opus 4.5 | anthropic/claude-opus-4-5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Claude Sonnet 4 | anthropic/claude-sonnet-4 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 4.5 | anthropic/claude-sonnet-4-5 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Grok 4 Fast | xai/grok-4-fast | 2M | 64K | Input: $0.2 Output: $0.5 Cache Read: $0.05 Cache Write: $0.2 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Released: 2025-09-19 |
| Grok 4 | xai/grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 Cache Write: $3 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image Out: text | Released: 2025-09-09 |
SAP AI Core¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| anthropic--claude-4.5-opus | anthropic--claude-4.5-opus | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-04-30 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| anthropic--claude-4-sonnet | anthropic--claude-4-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| anthropic--claude-4.5-sonnet | anthropic--claude-4.5-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| gemini-2.5-flash | gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.03 Input Audio: $1 | Model: 0.500 Completion: 2.500 Cache: 0.030 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-25 Updated: 2025-06-05 |
| anthropic--claude-3-sonnet | anthropic--claude-3-sonnet | 200K | 4.1K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-03-04 |
| anthropic--claude-3.7-sonnet | anthropic--claude-3.7-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-31 | In: text, image, pdf Out: text | Released: 2025-02-24 |
| anthropic--claude-3.5-sonnet | anthropic--claude-3.5-sonnet | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04-30 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| anthropic--claude-4.5-haiku | anthropic--claude-4.5-haiku | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-01 |
| gpt-5 | gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| anthropic--claude-3-opus | anthropic--claude-3-opus | 200K | 4.1K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-02-29 |
| gpt-5-mini | gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| anthropic--claude-3-haiku | anthropic--claude-3-haiku | 200K | 4.1K | Input: $0.25 Output: $1.25 Cache Read: $0.03 Cache Write: $0.3 | Model: 0.125 Completion: 5.000 Cache: 0.120 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-03-13 |
| gemini-2.5-pro | gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-25 Updated: 2025-06-05 |
| gpt-5-nano | gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.01 | Model: 0.025 Completion: 8.000 Cache: 0.200 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| anthropic--claude-4-opus | anthropic--claude-4-opus | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
Scaleway¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Voxtral Small 24B 2507 | voxtral-small-24b-2507 | 32K | 8.2K | Input: $0.15 Output: $0.35 | Model: 0.075 Completion: 2.333 | 📎 🔧 🌡️ | - | In: text, audio Out: text | Open Weights Released: 2025-07-01 |
| Qwen3 235B A22B Instruct 2507 | qwen3-235b-a22b-instruct-2507 | 260K | 8.2K | Input: $0.75 Output: $2.25 | Model: 0.375 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-01 |
| Llama-3.3-70B-Instruct | llama-3.3-70b-instruct | 100K | 4.1K | Input: $0.9 Output: $0.9 | Model: 0.450 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Mistral Small 3.2 24B Instruct (2506) | mistral-small-3.2-24b-instruct-2506 | 128K | 8.2K | Input: $0.15 Output: $0.35 | Model: 0.075 Completion: 2.333 | 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-06-20 |
| BGE Multilingual Gemma2 | bge-multilingual-gemma2 | 8.2K | 3.1K | Input: $0.13 Output: $0 | Model: 0.065 | - | - | In: text Out: text | Released: 2024-07-26 Updated: 2025-06-15 |
| GPT-OSS 120B | gpt-oss-120b | 128K | 8.2K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-01-01 |
| DeepSeek R1 Distill Llama 70B | deepseek-r1-distill-llama-70b | 32K | 4.1K | Input: $0.9 Output: $0.9 | Model: 0.450 Completion: 1.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-01-20 |
| Qwen3-Coder 30B-A3B Instruct | qwen3-coder-30b-a3b-instruct | 128K | 8.2K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04 |
| Whisper Large v3 | whisper-large-v3 | - | 4.1K | Input: $0.003 Output: $0 | Model: 0.002 | - | 2023-09 | In: audio Out: text | Open Weights Released: 2023-09-01 Updated: 2025-09-05 |
| Llama 3.1 8B Instruct | llama-3.1-8b-instruct | 128K | 16.4K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-01-01 |
| Devstral 2 123B Instruct (2512) | devstral-2-123b-instruct-2512 | 256K | 8.2K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-07 |
| Pixtral 12B 2409 | pixtral-12b-2409 | 128K | 4.1K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2024-09-25 |
| Mistral Nemo Instruct 2407 | mistral-nemo-instruct-2407 | 128K | 8.2K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-25 |
| Gemma-3-27B-IT | gemma-3-27b-it | 40K | 8.2K | Input: $0.25 Output: $0.5 | Model: 0.125 Completion: 2.000 | 📎 🧠 🔧 🌡️ | 2024-12 | In: text, image Out: text | Released: 2024-12-01 Updated: 2025-09-05 |
SiliconFlow¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| nex-agi/DeepSeek-V3.1-Nex-N1 | nex-agi/DeepSeek-V3.1-Nex-N1 | 131K | 131K | Input: $0.5 Output: $2 | Model: 0.250 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-01 Updated: 2025-11-25 |
| zai-org/GLM-4.5-Air | zai-org/GLM-4.5-Air | 131K | 131K | Input: $0.14 Output: $0.86 | Model: 0.070 Completion: 6.143 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-28 Updated: 2025-11-25 |
| zai-org/GLM-4.6 | zai-org/GLM-4.6 | 205K | 205K | Input: $0.5 Output: $1.9 | Model: 0.250 Completion: 3.800 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| zai-org/GLM-4.7 | zai-org/GLM-4.7 | 205K | 205K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-22 |
| zai-org/GLM-4.5V | zai-org/GLM-4.5V | 66K | 66K | Input: $0.14 Output: $0.86 | Model: 0.070 Completion: 6.143 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-13 Updated: 2025-11-25 |
| zai-org/GLM-4.6V | zai-org/GLM-4.6V | 131K | 131K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-12-07 |
| zai-org/GLM-4.5 | zai-org/GLM-4.5 | 131K | 131K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-28 Updated: 2025-11-25 |
| zai-org/GLM-5 | zai-org/GLM-5 | 205K | 205K | Input: $1 Output: $3.2 | Model: 0.500 Completion: 3.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-12 |
| MiniMaxAI/MiniMax-M2.1 | MiniMaxAI/MiniMax-M2.1 | 197K | 131K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-23 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 131K | 131K | Input: $0.18 Output: $0.18 | Model: 0.090 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-20 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | 131K | 131K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-20 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-V3.2-Exp | deepseek-ai/DeepSeek-V3.2-Exp | 164K | 164K | Input: $0.27 Output: $0.41 | Model: 0.135 Completion: 1.519 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-10 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-R1 | deepseek-ai/DeepSeek-R1 | 164K | 164K | Input: $0.5 Output: $2.18 | Model: 0.250 Completion: 4.360 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-05-28 Updated: 2025-11-25 |
| deepseek-ai/deepseek-vl2 | deepseek-ai/deepseek-vl2 | 4K | 4K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-12-13 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-V3.1 | deepseek-ai/DeepSeek-V3.1 | 164K | 164K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-25 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-V3.2 | deepseek-ai/DeepSeek-V3.2 | 164K | 164K | Input: $0.27 Output: $0.42 | Model: 0.135 Completion: 1.556 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-03 |
| deepseek-ai/DeepSeek-V3 | deepseek-ai/DeepSeek-V3 | 164K | 164K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-26 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-V3.1-Terminus | deepseek-ai/DeepSeek-V3.1-Terminus | 164K | 164K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-29 Updated: 2025-11-25 |
| ByteDance-Seed/Seed-OSS-36B-Instruct | ByteDance-Seed/Seed-OSS-36B-Instruct | 262K | 262K | Input: $0.21 Output: $0.57 | Model: 0.105 Completion: 2.714 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-04 Updated: 2025-11-25 |
| tencent/Hunyuan-A13B-Instruct | tencent/Hunyuan-A13B-Instruct | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-06-30 Updated: 2025-11-25 |
| tencent/Hunyuan-MT-7B | tencent/Hunyuan-MT-7B | 33K | 33K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-18 Updated: 2025-11-25 |
| moonshotai/Kimi-K2-Instruct | moonshotai/Kimi-K2-Instruct | 131K | 131K | Input: $0.58 Output: $2.29 | Model: 0.290 Completion: 3.948 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-13 Updated: 2025-11-25 |
| moonshotai/Kimi-K2-Instruct-0905 | moonshotai/Kimi-K2-Instruct-0905 | 262K | 262K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-08 Updated: 2025-11-25 |
| moonshotai/Kimi-K2.5 | moonshotai/Kimi-K2.5 | 262K | 262K | Input: $0.55 Output: $3 | Model: 0.275 Completion: 5.455 | 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01-27 |
| moonshotai/Kimi-K2-Thinking | moonshotai/Kimi-K2-Thinking | 262K | 262K | Input: $0.55 Output: $2.5 | Model: 0.275 Completion: 4.545 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-11-07 Updated: 2025-11-25 |
| inclusionAI/Ling-flash-2.0 | inclusionAI/Ling-flash-2.0 | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-18 Updated: 2025-11-25 |
| inclusionAI/Ring-flash-2.0 | inclusionAI/Ring-flash-2.0 | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-29 Updated: 2025-11-25 |
| inclusionAI/Ling-mini-2.0 | inclusionAI/Ling-mini-2.0 | 131K | 131K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-10 Updated: 2025-11-25 |
| baidu/ERNIE-4.5-300B-A47B | baidu/ERNIE-4.5-300B-A47B | 131K | 131K | Input: $0.28 Output: $1.1 | Model: 0.140 Completion: 3.929 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-02 Updated: 2025-11-25 |
| stepfun-ai/Step-3.5-Flash | stepfun-ai/Step-3.5-Flash | 262K | 262K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-11 |
| meta-llama/Meta-Llama-3.1-8B-Instruct | meta-llama/Meta-Llama-3.1-8B-Instruct | 33K | 4K | Input: $0.06 Output: $0.06 | Model: 0.030 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-23 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-30B-A3B-Thinking | Qwen/Qwen3-VL-30B-A3B-Thinking | 262K | 262K | Input: $0.29 Output: $1 | Model: 0.145 Completion: 3.448 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-11 Updated: 2025-11-25 |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | Qwen/Qwen3-30B-A3B-Instruct-2507 | 262K | 262K | Input: $0.09 Output: $0.3 | Model: 0.045 Completion: 3.333 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-30 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-235B-A22B-Instruct | Qwen/Qwen3-VL-235B-A22B-Instruct | 262K | 262K | Input: $0.3 Output: $1.5 | Model: 0.150 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-32B-Instruct | Qwen/Qwen3-VL-32B-Instruct | 262K | 262K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-21 Updated: 2025-11-25 |
| Qwen/QwQ-32B | Qwen/QwQ-32B | 131K | 131K | Input: $0.15 Output: $0.58 | Model: 0.075 Completion: 3.867 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-03-06 Updated: 2025-11-25 |
| Qwen/Qwen3-32B | Qwen/Qwen3-32B | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-30 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-235B-A22B-Thinking | Qwen/Qwen3-VL-235B-A22B-Thinking | 262K | 262K | Input: $0.45 Output: $3.5 | Model: 0.225 Completion: 7.778 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | 262K | 262K | Input: $0.14 Output: $1.4 | Model: 0.070 Completion: 10.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-18 Updated: 2025-11-25 |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262K | 262K | Input: $0.13 Output: $0.6 | Model: 0.065 Completion: 4.615 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-28 Updated: 2025-11-25 |
| Qwen/Qwen3-Omni-30B-A3B-Instruct | Qwen/Qwen3-Omni-30B-A3B-Instruct | 66K | 66K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image, audio Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen2.5-VL-7B-Instruct | Qwen/Qwen2.5-VL-7B-Instruct | 33K | 4K | Input: $0.05 Output: $0.05 | Model: 0.025 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-01-28 Updated: 2025-11-25 |
| Qwen/Qwen3-30B-A3B-Thinking-2507 | Qwen/Qwen3-30B-A3B-Thinking-2507 | 262K | 131K | Input: $0.09 Output: $0.3 | Model: 0.045 Completion: 3.333 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-31 Updated: 2025-11-25 |
| Qwen/Qwen2.5-32B-Instruct | Qwen/Qwen2.5-32B-Instruct | 33K | 4K | Input: $0.18 Output: $0.18 | Model: 0.090 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-19 Updated: 2025-11-25 |
| Qwen/Qwen2.5-Coder-32B-Instruct | Qwen/Qwen2.5-Coder-32B-Instruct | 33K | 4K | Input: $0.18 Output: $0.18 | Model: 0.090 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-11-11 Updated: 2025-11-25 |
| Qwen/Qwen3-8B | Qwen/Qwen3-8B | 131K | 131K | Input: $0.06 Output: $0.06 | Model: 0.030 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-30 Updated: 2025-11-25 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct | 262K | 262K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-31 Updated: 2025-11-25 |
| Qwen/Qwen3-Omni-30B-A3B-Thinking | Qwen/Qwen3-Omni-30B-A3B-Thinking | 66K | 66K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen2.5-7B-Instruct | Qwen/Qwen2.5-7B-Instruct | 33K | 4K | Input: $0.05 Output: $0.05 | Model: 0.025 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen2.5-14B-Instruct | Qwen/Qwen2.5-14B-Instruct | 33K | 4K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen2.5-VL-72B-Instruct | Qwen/Qwen2.5-VL-72B-Instruct | 131K | 4K | Input: $0.59 Output: $0.59 | Model: 0.295 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-01-28 Updated: 2025-11-25 |
| Qwen/Qwen2.5-72B-Instruct | Qwen/Qwen2.5-72B-Instruct | 33K | 4K | Input: $0.59 Output: $0.59 | Model: 0.295 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen2.5-72B-Instruct-128K | Qwen/Qwen2.5-72B-Instruct-128K | 131K | 4K | Input: $0.59 Output: $0.59 | Model: 0.295 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen3-235B-A22B | Qwen/Qwen3-235B-A22B | 131K | 131K | Input: $0.35 Output: $1.42 | Model: 0.175 Completion: 4.057 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-30 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-8B-Instruct | Qwen/Qwen3-VL-8B-Instruct | 262K | 262K | Input: $0.18 Output: $0.68 | Model: 0.090 Completion: 3.778 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-15 Updated: 2025-11-25 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | Qwen/Qwen3-Next-80B-A3B-Thinking | 262K | 262K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-25 Updated: 2025-11-25 |
| Qwen/Qwen3-Omni-30B-A3B-Captioner | Qwen/Qwen3-Omni-30B-A3B-Captioner | 66K | 66K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | - | In: audio Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-30B-A3B-Instruct | Qwen/Qwen3-VL-30B-A3B-Instruct | 262K | 262K | Input: $0.29 Output: $1 | Model: 0.145 Completion: 3.448 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-05 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-8B-Thinking | Qwen/Qwen3-VL-8B-Thinking | 262K | 262K | Input: $0.18 Output: $2 | Model: 0.090 Completion: 11.111 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-15 Updated: 2025-11-25 |
| Qwen/Qwen3-Coder-30B-A3B-Instruct | Qwen/Qwen3-Coder-30B-A3B-Instruct | 262K | 262K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-01 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-32B-Thinking | Qwen/Qwen3-VL-32B-Thinking | 262K | 262K | Input: $0.2 Output: $1.5 | Model: 0.100 Completion: 7.500 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-21 Updated: 2025-11-25 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262K | 262K | Input: $0.09 Output: $0.6 | Model: 0.045 Completion: 6.667 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-23 Updated: 2025-11-25 |
| Qwen/Qwen3-14B | Qwen/Qwen3-14B | 131K | 131K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-30 Updated: 2025-11-25 |
| Qwen/Qwen2.5-VL-32B-Instruct | Qwen/Qwen2.5-VL-32B-Instruct | 131K | 131K | Input: $0.27 Output: $0.27 | Model: 0.135 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-03-24 Updated: 2025-11-25 |
| openai/gpt-oss-120b | openai/gpt-oss-120b | 131K | 8K | Input: $0.05 Output: $0.45 | Model: 0.025 Completion: 9.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-13 Updated: 2025-11-25 |
| openai/gpt-oss-20b | openai/gpt-oss-20b | 131K | 8K | Input: $0.04 Output: $0.18 | Model: 0.020 Completion: 4.500 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-13 Updated: 2025-11-25 |
| THUDM/GLM-4-32B-0414 | THUDM/GLM-4-32B-0414 | 33K | 33K | Input: $0.27 Output: $0.27 | Model: 0.135 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
| THUDM/GLM-4-9B-0414 | THUDM/GLM-4-9B-0414 | 33K | 33K | Input: $0.086 Output: $0.086 | Model: 0.043 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
| THUDM/GLM-Z1-32B-0414 | THUDM/GLM-Z1-32B-0414 | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
| THUDM/GLM-Z1-9B-0414 | THUDM/GLM-Z1-9B-0414 | 131K | 131K | Input: $0.086 Output: $0.086 | Model: 0.043 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
SiliconFlow (China)¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| zai-org/GLM-4.6V | zai-org/GLM-4.6V | 131K | 131K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-12-07 |
| zai-org/GLM-4.5V | zai-org/GLM-4.5V | 66K | 66K | Input: $0.14 Output: $0.86 | Model: 0.070 Completion: 6.143 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-08-13 Updated: 2025-11-25 |
| zai-org/GLM-4.6 | zai-org/GLM-4.6 | 205K | 205K | Input: $0.5 Output: $1.9 | Model: 0.250 Completion: 3.800 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| zai-org/GLM-4.5-Air | zai-org/GLM-4.5-Air | 131K | 131K | Input: $0.14 Output: $0.86 | Model: 0.070 Completion: 6.143 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-28 Updated: 2025-11-25 |
| Pro/zai-org/GLM-4.7 | Pro/zai-org/GLM-4.7 | 205K | 205K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-22 |
| Pro/zai-org/GLM-5 | Pro/zai-org/GLM-5 | 205K | 205K | Input: $1 Output: $3.2 | Model: 0.500 Completion: 3.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-12 |
| Pro/MiniMaxAI/MiniMax-M2.5 | Pro/MiniMaxAI/MiniMax-M2.5 | 192K | 131K | Input: $0.3 Output: $1.22 | Model: 0.150 Completion: 4.067 | 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-13 |
| Pro/MiniMaxAI/MiniMax-M2.1 | Pro/MiniMaxAI/MiniMax-M2.1 | 197K | 131K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-23 |
| Pro/deepseek-ai/DeepSeek-R1 | Pro/deepseek-ai/DeepSeek-R1 | 164K | 164K | Input: $0.5 Output: $2.18 | Model: 0.250 Completion: 4.360 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-05-28 Updated: 2025-11-25 |
| Pro/deepseek-ai/DeepSeek-V3.2 | Pro/deepseek-ai/DeepSeek-V3.2 | 164K | 164K | Input: $0.27 Output: $0.42 | Model: 0.135 Completion: 1.556 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-03 |
| Pro/deepseek-ai/DeepSeek-V3 | Pro/deepseek-ai/DeepSeek-V3 | 164K | 164K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-26 Updated: 2025-11-25 |
| Pro/deepseek-ai/DeepSeek-V3.1-Terminus | Pro/deepseek-ai/DeepSeek-V3.1-Terminus | 164K | 164K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-29 Updated: 2025-11-25 |
| Pro/moonshotai/Kimi-K2-Instruct-0905 | Pro/moonshotai/Kimi-K2-Instruct-0905 | 262K | 262K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-08 Updated: 2025-11-25 |
| Pro/moonshotai/Kimi-K2.5 | Pro/moonshotai/Kimi-K2.5 | 262K | 262K | Input: $0.55 Output: $3 | Model: 0.275 Completion: 5.455 | 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-01-27 |
| Pro/moonshotai/Kimi-K2-Thinking | Pro/moonshotai/Kimi-K2-Thinking | 262K | 262K | Input: $0.55 Output: $2.5 | Model: 0.275 Completion: 4.545 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-11-07 Updated: 2025-11-25 |
| PaddlePaddle/PaddleOCR-VL-1.5 | PaddlePaddle/PaddleOCR-VL-1.5 | 16.4K | 16.4K | Input: $0 Output: $0 | - | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-01-29 |
| PaddlePaddle/PaddleOCR-VL | PaddlePaddle/PaddleOCR-VL | 16.4K | 16.4K | Input: $0 Output: $0 | - | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-10-16 |
| Kwaipilot/KAT-Dev | Kwaipilot/KAT-Dev | 128K | 128K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-27 Updated: 2026-01-16 |
| deepseek-ai/DeepSeek-OCR | deepseek-ai/DeepSeek-OCR | 8.2K | 8.2K | Input: $0 Output: $0 | - | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-10-20 |
| deepseek-ai/DeepSeek-V3.1-Terminus | deepseek-ai/DeepSeek-V3.1-Terminus | 164K | 164K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-29 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-V3 | deepseek-ai/DeepSeek-V3 | 164K | 164K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-12-26 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-V3.2 | deepseek-ai/DeepSeek-V3.2 | 164K | 164K | Input: $0.27 Output: $0.42 | Model: 0.135 Completion: 1.556 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-03 |
| deepseek-ai/deepseek-vl2 | deepseek-ai/deepseek-vl2 | 4K | 4K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2024-12-13 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-R1 | deepseek-ai/DeepSeek-R1 | 164K | 164K | Input: $0.5 Output: $2.18 | Model: 0.250 Completion: 4.360 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-05-28 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | 131K | 131K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-20 Updated: 2025-11-25 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 131K | 131K | Input: $0.18 Output: $0.18 | Model: 0.090 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-01-20 Updated: 2025-11-25 |
| ByteDance-Seed/Seed-OSS-36B-Instruct | ByteDance-Seed/Seed-OSS-36B-Instruct | 262K | 262K | Input: $0.21 Output: $0.57 | Model: 0.105 Completion: 2.714 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-04 Updated: 2025-11-25 |
| tencent/Hunyuan-MT-7B | tencent/Hunyuan-MT-7B | 33K | 33K | Input: $0 Output: $0 | - | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-18 Updated: 2025-11-25 |
| tencent/Hunyuan-A13B-Instruct | tencent/Hunyuan-A13B-Instruct | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-06-30 Updated: 2025-11-25 |
| ascend-tribe/pangu-pro-moe | ascend-tribe/pangu-pro-moe | 128K | 128K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🧠 🌡️ | - | In: text Out: text | Released: 2025-07-02 Updated: 2026-01-16 |
| moonshotai/Kimi-K2-Thinking | moonshotai/Kimi-K2-Thinking | 262K | 262K | Input: $0.55 Output: $2.5 | Model: 0.275 Completion: 4.545 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-11-07 Updated: 2025-11-25 |
| moonshotai/Kimi-K2-Instruct-0905 | moonshotai/Kimi-K2-Instruct-0905 | 262K | 262K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-08 Updated: 2025-11-25 |
| inclusionAI/Ling-mini-2.0 | inclusionAI/Ling-mini-2.0 | 131K | 131K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-10 Updated: 2025-11-25 |
| inclusionAI/Ring-flash-2.0 | inclusionAI/Ring-flash-2.0 | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-29 Updated: 2025-11-25 |
| inclusionAI/Ling-flash-2.0 | inclusionAI/Ling-flash-2.0 | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-18 Updated: 2025-11-25 |
| baidu/ERNIE-4.5-300B-A47B | baidu/ERNIE-4.5-300B-A47B | 131K | 131K | Input: $0.28 Output: $1.1 | Model: 0.140 Completion: 3.929 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-02 Updated: 2025-11-25 |
| stepfun-ai/Step-3.5-Flash | stepfun-ai/Step-3.5-Flash | 262K | 262K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-11 |
| Qwen/Qwen2.5-VL-32B-Instruct | Qwen/Qwen2.5-VL-32B-Instruct | 131K | 131K | Input: $0.27 Output: $0.27 | Model: 0.135 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-03-24 Updated: 2025-11-25 |
| Qwen/Qwen3-14B | Qwen/Qwen3-14B | 131K | 131K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-30 Updated: 2025-11-25 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262K | 262K | Input: $0.09 Output: $0.6 | Model: 0.045 Completion: 6.667 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-23 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-32B-Thinking | Qwen/Qwen3-VL-32B-Thinking | 262K | 262K | Input: $0.2 Output: $1.5 | Model: 0.100 Completion: 7.500 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-21 Updated: 2025-11-25 |
| Qwen/Qwen3-Coder-30B-A3B-Instruct | Qwen/Qwen3-Coder-30B-A3B-Instruct | 262K | 262K | Input: $0.07 Output: $0.28 | Model: 0.035 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-01 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-8B-Thinking | Qwen/Qwen3-VL-8B-Thinking | 262K | 262K | Input: $0.18 Output: $2 | Model: 0.090 Completion: 11.111 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-15 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-30B-A3B-Instruct | Qwen/Qwen3-VL-30B-A3B-Instruct | 262K | 262K | Input: $0.29 Output: $1 | Model: 0.145 Completion: 3.448 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-05 Updated: 2025-11-25 |
| Qwen/Qwen3-Omni-30B-A3B-Captioner | Qwen/Qwen3-Omni-30B-A3B-Captioner | 66K | 66K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | - | In: audio Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | Qwen/Qwen3-Next-80B-A3B-Thinking | 262K | 262K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-25 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-8B-Instruct | Qwen/Qwen3-VL-8B-Instruct | 262K | 262K | Input: $0.18 Output: $0.68 | Model: 0.090 Completion: 3.778 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-15 Updated: 2025-11-25 |
| Qwen/Qwen2.5-72B-Instruct-128K | Qwen/Qwen2.5-72B-Instruct-128K | 131K | 4K | Input: $0.59 Output: $0.59 | Model: 0.295 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen2.5-72B-Instruct | Qwen/Qwen2.5-72B-Instruct | 33K | 4K | Input: $0.59 Output: $0.59 | Model: 0.295 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen2.5-VL-72B-Instruct | Qwen/Qwen2.5-VL-72B-Instruct | 131K | 4K | Input: $0.59 Output: $0.59 | Model: 0.295 Completion: 1.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-01-28 Updated: 2025-11-25 |
| Qwen/Qwen2.5-14B-Instruct | Qwen/Qwen2.5-14B-Instruct | 33K | 4K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen2.5-7B-Instruct | Qwen/Qwen2.5-7B-Instruct | 33K | 4K | Input: $0.05 Output: $0.05 | Model: 0.025 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-18 Updated: 2025-11-25 |
| Qwen/Qwen3-Omni-30B-A3B-Thinking | Qwen/Qwen3-Omni-30B-A3B-Thinking | 66K | 66K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct | 262K | 262K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-31 Updated: 2025-11-25 |
| Qwen/Qwen3-8B | Qwen/Qwen3-8B | 131K | 131K | Input: $0.06 Output: $0.06 | Model: 0.030 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-30 Updated: 2025-11-25 |
| Qwen/Qwen2.5-Coder-32B-Instruct | Qwen/Qwen2.5-Coder-32B-Instruct | 33K | 4K | Input: $0.18 Output: $0.18 | Model: 0.090 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-11-11 Updated: 2025-11-25 |
| Qwen/Qwen2.5-32B-Instruct | Qwen/Qwen2.5-32B-Instruct | 33K | 4K | Input: $0.18 Output: $0.18 | Model: 0.090 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2024-09-19 Updated: 2025-11-25 |
| Qwen/Qwen3-30B-A3B-Thinking-2507 | Qwen/Qwen3-30B-A3B-Thinking-2507 | 262K | 131K | Input: $0.09 Output: $0.3 | Model: 0.045 Completion: 3.333 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-31 Updated: 2025-11-25 |
| Qwen/Qwen3-Omni-30B-A3B-Instruct | Qwen/Qwen3-Omni-30B-A3B-Instruct | 66K | 66K | Input: $0.1 Output: $0.4 | Model: 0.050 Completion: 4.000 | 📎 🔧 🌡️ | - | In: text, image, audio Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262K | 262K | Input: $0.13 Output: $0.6 | Model: 0.065 Completion: 4.615 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-28 Updated: 2025-11-25 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | 262K | 262K | Input: $0.14 Output: $1.4 | Model: 0.070 Completion: 10.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-18 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-235B-A22B-Thinking | Qwen/Qwen3-VL-235B-A22B-Thinking | 262K | 262K | Input: $0.45 Output: $3.5 | Model: 0.225 Completion: 7.778 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-32B | Qwen/Qwen3-32B | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-30 Updated: 2025-11-25 |
| Qwen/QwQ-32B | Qwen/QwQ-32B | 131K | 131K | Input: $0.15 Output: $0.58 | Model: 0.075 Completion: 3.867 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-03-06 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-32B-Instruct | Qwen/Qwen3-VL-32B-Instruct | 262K | 262K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-21 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-235B-A22B-Instruct | Qwen/Qwen3-VL-235B-A22B-Instruct | 262K | 262K | Input: $0.3 Output: $1.5 | Model: 0.150 Completion: 5.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-04 Updated: 2025-11-25 |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | Qwen/Qwen3-30B-A3B-Instruct-2507 | 262K | 262K | Input: $0.09 Output: $0.3 | Model: 0.045 Completion: 3.333 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-30 Updated: 2025-11-25 |
| Qwen/Qwen3-VL-30B-A3B-Thinking | Qwen/Qwen3-VL-30B-A3B-Thinking | 262K | 262K | Input: $0.29 Output: $1 | Model: 0.145 Completion: 3.448 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-10-11 Updated: 2025-11-25 |
| THUDM/GLM-Z1-9B-0414 | THUDM/GLM-Z1-9B-0414 | 131K | 131K | Input: $0.086 Output: $0.086 | Model: 0.043 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
| THUDM/GLM-Z1-32B-0414 | THUDM/GLM-Z1-32B-0414 | 131K | 131K | Input: $0.14 Output: $0.57 | Model: 0.070 Completion: 4.071 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
| THUDM/GLM-4-9B-0414 | THUDM/GLM-4-9B-0414 | 33K | 33K | Input: $0.086 Output: $0.086 | Model: 0.043 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
| THUDM/GLM-4-32B-0414 | THUDM/GLM-4-32B-0414 | 33K | 33K | Input: $0.27 Output: $0.27 | Model: 0.135 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-04-18 Updated: 2025-11-25 |
STACKIT¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| E5 Mistral 7B | intfloat/e5-mistral-7b-instruct | 4.1K | 4.1K | Input: $0.02 Output: $0.02 | Model: 0.010 Completion: 1.000 | - | - | In: text Out: text | Open Weights Released: 2023-12-11 |
| Llama 3.1 8B | neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8 | 128K | 8.2K | Input: $0.16 Output: $0.27 | Model: 0.080 Completion: 1.688 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-23 |
| Mistral Nemo | neuralmagic/Mistral-Nemo-Instruct-2407-FP8 | 128K | 8.2K | Input: $0.49 Output: $0.71 | Model: 0.245 Completion: 1.449 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-07-01 |
| Gemma 3 27B | google/gemma-3-27b-it | 37K | 8.2K | Input: $0.49 Output: $0.71 | Model: 0.245 Completion: 1.449 | 📎 🌡️ | - | In: text, image Out: text | Open Weights Released: 2025-05-17 |
| Qwen3-VL Embedding 8B | Qwen/Qwen3-VL-Embedding-8B | 32K | 4.1K | Input: $0.09 Output: $0.09 | Model: 0.045 Completion: 1.000 | 📎 | - | In: text, image Out: text | Open Weights Released: 2026-02-05 |
| Qwen3-VL 235B | Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 | 218K | 8.2K | Input: $1.64 Output: $1.91 | Model: 0.820 Completion: 1.165 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2024-11-01 |
| GPT-OSS 120B | openai/gpt-oss-120b | 131K | 8.2K | Input: $0.49 Output: $0.71 | Model: 0.245 Completion: 1.449 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| Llama 3.3 70B | cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic | 128K | 8.2K | Input: $0.49 Output: $0.71 | Model: 0.245 Completion: 1.449 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2024-12-05 |
StepFun¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.5 Flash | step-3.5-flash | 256K | 256K | Input: $0.096 Output: $0.288 Cache Read: $0.019 | Model: 0.048 Completion: 3.000 Cache: 0.198 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2026-01-29 Updated: 2026-02-13 |
| Step 2 (16K) | step-2-16k | 16.4K | 8.2K | Input: $5.21 Output: $16.44 Cache Read: $1.04 | Model: 2.605 Completion: 3.155 Cache: 0.200 | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Released: 2025-01-01 Updated: 2026-02-13 |
| Step 1 (32K) | step-1-32k | 32.8K | 32.8K | Input: $2.05 Output: $9.59 Cache Read: $0.41 | Model: 1.025 Completion: 4.678 Cache: 0.200 | 🧠 🔧 🌡️ | 2024-06 | In: text Out: text | Released: 2025-01-01 Updated: 2026-02-13 |
submodel¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 4.5 Air | zai-org/GLM-4.5-Air | 131.1K | 131.1K | Input: $0.1 Output: $0.5 | Model: 0.050 Completion: 5.000 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM 4.5 FP8 | zai-org/GLM-4.5-FP8 | 131.1K | 131.1K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-07-28 |
| DeepSeek R1 0528 | deepseek-ai/DeepSeek-R1-0528 | 75K | 163.8K | Input: $0.5 Output: $2.15 | Model: 0.250 Completion: 4.300 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-23 |
| DeepSeek V3.1 | deepseek-ai/DeepSeek-V3.1 | 75K | 163.8K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-23 |
| DeepSeek V3 0324 | deepseek-ai/DeepSeek-V3-0324 | 75K | 163.8K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-23 |
| Qwen3 235B A22B Thinking 2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262.1K | 131.1K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-23 |
| Qwen3 Coder 480B A35B Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | 262.1K | 262.1K | Input: $0.2 Output: $0.8 | Model: 0.100 Completion: 4.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-23 |
| Qwen3 235B A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262.1K | 131.1K | Input: $0.2 Output: $0.3 | Model: 0.100 Completion: 1.500 | 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-23 |
| GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 32.8K | Input: $0.1 Output: $0.5 | Model: 0.050 Completion: 5.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-23 |
Synthetic¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| MiniMax-M2 | hf:MiniMaxAI/MiniMax-M2 | 196.6K | 131K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-10-27 |
| MiniMax-M2.1 | hf:MiniMaxAI/MiniMax-M2.1 | 204.8K | 131.1K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-23 |
| DeepSeek R1 | hf:deepseek-ai/DeepSeek-R1 | 128K | 128K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-01-20 |
| DeepSeek R1 (0528) | hf:deepseek-ai/DeepSeek-R1-0528 | 128K | 128K | Input: $3 Output: $8 | Model: 1.500 Completion: 2.667 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-01 |
| DeepSeek V3.1 | hf:deepseek-ai/DeepSeek-V3.1 | 128K | 128K | Input: $0.56 Output: $1.68 | Model: 0.280 Completion: 3.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-21 |
| DeepSeek V3.2 | hf:deepseek-ai/DeepSeek-V3.2 | 162.8K | 8K | Input: $0.27 Output: $0.4 Cache Read: $0.27 Cache Write: $0 | Model: 0.135 Completion: 1.481 Cache: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-01 |
| DeepSeek V3 (0324) | hf:deepseek-ai/DeepSeek-V3-0324 | 128K | 128K | Input: $1.2 Output: $1.2 | Model: 0.600 Completion: 1.000 | 🔧 🌡️ | - | In: text Out: text | Released: 2025-08-01 |
| DeepSeek V3 | hf:deepseek-ai/DeepSeek-V3 | 128K | 128K | Input: $1.25 Output: $1.25 | Model: 0.625 Completion: 1.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-01-20 Updated: 2025-05-29 |
| DeepSeek V3.1 Terminus | hf:deepseek-ai/DeepSeek-V3.1-Terminus | 128K | 128K | Input: $1.2 Output: $1.2 | Model: 0.600 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-09-22 Updated: 2025-09-25 |
| Kimi K2 0905 | hf:moonshotai/Kimi-K2-Instruct-0905 | 262.1K | 32.8K | Input: $1.2 Output: $1.2 | Model: 0.600 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2.5 | hf:moonshotai/Kimi-K2.5 | 262.1K | 65.5K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | 2025-01 | In: text, image Out: text | Open Weights Released: 2026-01 |
| Kimi K2 Thinking | hf:moonshotai/Kimi-K2-Thinking | 262.1K | 262.1K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2025-11-07 |
| GPT OSS 120B | hf:openai/gpt-oss-120b | 128K | 32.8K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-08-05 |
| Kimi K2.5 (NVFP4) | hf:nvidia/Kimi-K2.5-NVFP4 | 262.1K | 65.5K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | 2025-01 | In: text, image Out: text | Open Weights Released: 2026-01 |
| Llama-4-Scout-17B-16E-Instruct | hf:meta-llama/Llama-4-Scout-17B-16E-Instruct | 328K | 4.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Llama-3.1-405B-Instruct | hf:meta-llama/Llama-3.1-405B-Instruct | 128K | 32.8K | Input: $3 Output: $3 | Model: 1.500 Completion: 1.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama-3.1-70B-Instruct | hf:meta-llama/Llama-3.1-70B-Instruct | 128K | 32.8K | Input: $0.9 Output: $0.9 | Model: 0.450 Completion: 1.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama-3.1-8B-Instruct | hf:meta-llama/Llama-3.1-8B-Instruct | 128K | 32.8K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama-3.3-70B-Instruct | hf:meta-llama/Llama-3.3-70B-Instruct | 128K | 32.8K | Input: $0.9 Output: $0.9 | Model: 0.450 Completion: 1.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 524K | 4.1K | Input: $0.22 Output: $0.88 | Model: 0.110 Completion: 4.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| GLM 4.6 | hf:zai-org/GLM-4.6 | 200K | 64K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM 4.7 | hf:zai-org/GLM-4.7 | 200K | 64K | Input: $0.55 Output: $2.19 | Model: 0.275 Completion: 3.982 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| Qwen3 235B A22B Thinking 2507 | hf:Qwen/Qwen3-235B-A22B-Thinking-2507 | 256K | 32K | Input: $0.65 Output: $3 | Model: 0.325 Completion: 4.615 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen2.5-Coder-32B-Instruct | hf:Qwen/Qwen2.5-Coder-32B-Instruct | 32.8K | 32.8K | Input: $0.8 Output: $0.8 | Model: 0.400 Completion: 1.000 | 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-11-11 |
| Qwen 3 Coder 480B | hf:Qwen/Qwen3-Coder-480B-A35B-Instruct | 256K | 32K | Input: $2 Output: $2 | Model: 1.000 Completion: 1.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen 3 235B Instruct | hf:Qwen/Qwen3-235B-A22B-Instruct-2507 | 256K | 32K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 Updated: 2025-07-21 |
Together AI¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM 4.6 | zai-org/GLM-4.6 | 200K | 200K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7 | zai-org/GLM-4.7 | 200K | 200K | Input: $0.45 Output: $2 | Model: 0.225 Completion: 4.444 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-07-25 |
| GLM-5 | zai-org/GLM-5 | 202.8K | 131.1K | Input: $1 Output: $3.2 | Model: 0.500 Completion: 3.200 | 🧠 🔧 🌡️ | 2025-11 | In: text Out: text | Open Weights Released: 2026-02-11 |
| Rnj-1 Instruct | essentialai/Rnj-1-Instruct | 32.8K | 32.8K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-12-05 |
| MiniMax-M2.5 | MiniMaxAI/MiniMax-M2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 | Model: 0.150 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| DeepSeek V3.1 | deepseek-ai/DeepSeek-V3-1 | 131.1K | 131.1K | Input: $0.6 Output: $1.7 | Model: 0.300 Completion: 2.833 | 🧠 🔧 🌡️ | 2025-08 | In: text Out: text | Open Weights Released: 2025-08-21 |
| DeepSeek R1 | deepseek-ai/DeepSeek-R1 | 163.8K | 163.8K | Input: $3 Output: $7 | Model: 1.500 Completion: 2.333 | 🧠 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2024-12-26 Updated: 2025-03-24 |
| DeepSeek V3 | deepseek-ai/DeepSeek-V3 | 131.1K | 131.1K | Input: $1.25 Output: $1.25 | Model: 0.625 Completion: 1.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-01-20 Updated: 2025-05-29 |
| Kimi K2 Instruct | moonshotai/Kimi-K2-Instruct | 131.1K | 131.1K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-14 |
| Kimi K2 Instruct-0905 | moonshotai/Kimi-K2-Instruct-0905 | 262.1K | 262.1K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2025-09-05 |
| Kimi K2.5 | moonshotai/Kimi-K2.5 | 262.1K | 262.1K | Input: $0.5 Output: $2.8 | Model: 0.250 Completion: 5.600 | 🧠 🔧 🌡️ | 2026-01 | In: text, image Out: text | Open Weights Released: 2026-01-27 |
| Kimi K2 Thinking | moonshotai/Kimi-K2-Thinking | 262.1K | 262.1K | Input: $1.2 Output: $4 | Model: 0.600 Completion: 3.333 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-11-06 |
| Llama 3.3 70B | meta-llama/Llama-3.3-70B-Instruct-Turbo | 131.1K | 131.1K | Input: $0.88 Output: $0.88 | Model: 0.440 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Qwen3-Next-80B-A3B-Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | 262.1K | 262.1K | Input: $0.15 Output: $1.5 | Model: 0.075 Completion: 10.000 | 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen3 235B A22B Instruct 2507 FP8 | Qwen/Qwen3-235B-A22B-Instruct-2507-tput | 262.1K | 262.1K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen3.5 397B A17B | Qwen/Qwen3.5-397B-A17B | 262.1K | 130K | Input: $0.6 Output: $3.6 | Model: 0.300 Completion: 6.000 | 🧠 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-02-16 |
| Qwen3 Coder Next FP8 | Qwen/Qwen3-Coder-Next-FP8 | 262.1K | 262.1K | Input: $0.5 Output: $1.2 | Model: 0.250 Completion: 2.400 | 🧠 🔧 🌡️ | 2026-02-03 | In: text Out: text | Open Weights Released: 2026-02-03 |
| Qwen3 Coder 480B A35B Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | 262.1K | 262.1K | Input: $2 Output: $2 | Model: 1.000 Completion: 1.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 131.1K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-08 | In: text Out: text | Open Weights Released: 2025-08-05 |
Upstage¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| solar-pro2 | solar-pro2 | 65.5K | 8.2K | Input: $0.25 Output: $0.25 | Model: 0.125 Completion: 1.000 | 🧠 🔧 🌡️ | 2025-03 | In: text Out: text | Released: 2025-05-20 |
| solar-mini | solar-mini | 32.8K | 4.1K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🔧 🌡️ | 2024-09 | In: text Out: text | Released: 2024-06-12 Updated: 2025-04-22 |
| solar-pro3 | solar-pro3 | 131.1K | 8.2K | Input: $0.25 Output: $0.25 | Model: 0.125 Completion: 1.000 | 🧠 🔧 🌡️ | 2025-03 | In: text Out: text | Released: 2026-01 |
v0¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| v0-1.0-md | v0-1.0-md | 128K | 32K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-05-22 |
| v0-1.5-md | v0-1.5-md | 128K | 32K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-06-09 |
| v0-1.5-lg | v0-1.5-lg | 512K | 32K | Input: $15 Output: $75 | Model: 7.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-06-09 |
Venice AI¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Qwen 3 235B A22B Instruct 2507 | qwen3-235b-a22b-instruct-2507 | 128K | 32K | Input: $0.15 Output: $0.75 | Model: 0.075 Completion: 5.000 | 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-04-29 Updated: 2026-01-28 |
| Google Gemma 3 27B Instruct | google-gemma-3-27b-it | 198K | 49.5K | Input: $0.12 Output: $0.2 | Model: 0.060 Completion: 1.667 | 📎 🔧 🌡️ | 2025-07 | In: text, image Out: text | Open Weights Released: 2025-11-04 Updated: 2026-01-28 |
| Claude Opus 4.5 | claude-opus-45 | 198K | 49.5K | Input: $6 Output: $30 Cache Read: $0.6 Cache Write: $7.5 | Model: 3.000 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03 | In: text, image, pdf Out: text | Released: 2025-12-06 Updated: 2026-01-28 |
| Qwen 3 Coder 480b | qwen3-coder-480b-a35b-instruct | 256K | 64K | Input: $0.75 Output: $3 | Model: 0.375 Completion: 4.000 | 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-04-29 Updated: 2026-01-28 |
| Claude Opus 4.6 | claude-opus-4-6 | 1M | 128K | Input: $6 Output: $30 Cache Read: $0.6 Cache Write: $7.5 | Model: 3.000 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-02-05 Updated: 2026-02-18 |
| Grok Code Fast 1 | grok-code-fast-1 | 256K | 64K | Input: $0.25 Output: $1.87 Cache Read: $0.03 | Model: 0.125 Completion: 7.480 Cache: 0.120 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-12-01 Updated: 2026-01-28 |
| GLM 5 | zai-org-glm-5 | 198K | 49.5K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-11 |
| GLM 4.7 | zai-org-glm-4.7 | 198K | 49.5K | Input: $0.55 Output: $2.65 Cache Read: $0.11 | Model: 0.275 Completion: 4.818 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-24 Updated: 2026-01-28 |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 1M | 128K | Input: $3.75 Output: $18.75 Cache Read: $0.375 Cache Write: $4.69 | Model: 1.875 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2026-02-17 Updated: 2026-02-19 |
| Kimi K2.5 | kimi-k2-5 | 256K | 64K | Input: $0.75 Output: $3.75 Cache Read: $0.125 | Model: 0.375 Completion: 5.000 Cache: 0.167 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image Out: text | Open Weights Released: 2026-01-27 Updated: 2026-01-28 |
| Venice Medium | mistral-31-24b | 128K | 32K | Input: $0.5 Output: $2 | Model: 0.250 Completion: 4.000 | 📎 🔧 🌡️ | 2023-10 | In: text, image Out: text | Open Weights Released: 2025-03-18 Updated: 2026-01-28 |
| Venice Small | qwen3-4b | 32K | 8K | Input: $0.05 Output: $0.15 | Model: 0.025 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-04-29 Updated: 2026-01-28 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 256K | 64K | Input: $0.7 Output: $3.75 Cache Read: $0.07 | Model: 0.350 Completion: 5.357 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-12-19 Updated: 2026-01-28 |
| GLM 4.7 Flash Heretic | olafangensan-glm-4.7-flash-heretic | 128K | 32K | Input: $0.14 Output: $0.8 | Model: 0.070 Completion: 5.714 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-04 Updated: 2026-02-18 |
| MiniMax M2.5 | minimax-m25 | 198K | 32K | Input: $0.4 Output: $1.6 Cache Read: $0.04 | Model: 0.200 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 Updated: 2026-02-19 |
| GLM 4.7 Flash | zai-org-glm-4.7-flash | 128K | 32K | Input: $0.125 Output: $0.5 | Model: 0.063 Completion: 4.000 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-01-29 Updated: 2026-02-10 |
| OpenAI GPT OSS 120B | openai-gpt-oss-120b | 128K | 32K | Input: $0.07 Output: $0.3 | Model: 0.035 Completion: 4.286 | 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-11-06 Updated: 2026-01-28 |
| Grok 4.1 Fast | grok-41-fast | 256K | 64K | Input: $0.5 Output: $1.25 Cache Read: $0.125 | Model: 0.250 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-12-01 Updated: 2026-01-28 |
| GPT-5.2 | openai-gpt-52 | 256K | 64K | Input: $2.19 Output: $17.5 Cache Read: $0.219 | Model: 1.095 Completion: 7.991 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-08-31 | In: text Out: text | Released: 2025-12-13 Updated: 2026-01-28 |
| DeepSeek V3.2 | deepseek-v3.2 | 160K | 40K | Input: $0.4 Output: $1 Cache Read: $0.2 | Model: 0.200 Completion: 2.500 Cache: 0.500 | 🧠 🌡️ | 2025-10 | In: text Out: text | Open Weights Released: 2025-12-04 Updated: 2026-01-28 |
| Gemini 3.1 Pro Preview | gemini-3-1-pro-preview | 1M | 65K | Input: $2.5 Output: $15 Cache Read: $0.5 Cache Write: $0.5 | Model: 1.250 Completion: 6.000 Cache: 0.200 | 📎 🧠 🔧 🌡️ | - | In: text, image, audio, video Out: text | Released: 2026-02-19 Updated: 2026-02-24 |
| Llama 3.3 70B | llama-3.3-70b | 128K | 32K | Input: $0.7 Output: $2.8 | Model: 0.350 Completion: 4.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2025-04-06 Updated: 2026-01-28 |
| Qwen 3 Next 80b | qwen3-next-80b | 256K | 64K | Input: $0.35 Output: $1.9 | Model: 0.175 Completion: 5.429 | 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-04-29 Updated: 2026-01-28 |
| Hermes 3 Llama 3.1 405b | hermes-3-llama-3.1-405b | 128K | 32K | Input: $1.1 Output: $3 | Model: 0.550 Completion: 2.727 | 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2025-09-25 Updated: 2026-01-28 |
| Kimi K2 Thinking | kimi-k2-thinking | 256K | 64K | Input: $0.75 Output: $3.2 Cache Read: $0.375 | Model: 0.375 Completion: 4.267 Cache: 0.500 | 🧠 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2025-12-10 Updated: 2026-01-28 |
| MiniMax M2.1 | minimax-m21 | 198K | 49.5K | Input: $0.4 Output: $1.6 Cache Read: $0.04 | Model: 0.200 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2025-12-01 Updated: 2026-01-28 |
| Qwen 3 235B A22B Thinking 2507 | qwen3-235b-a22b-thinking-2507 | 128K | 32K | Input: $0.45 Output: $3.5 | Model: 0.225 Completion: 7.778 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-04-29 Updated: 2026-01-28 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 198K | 49.5K | Input: $2.5 Output: $15 Cache Read: $0.625 | Model: 1.250 Completion: 6.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2024-04 | In: text, image, audio, video Out: text | Released: 2025-12-02 Updated: 2026-01-28 |
| Llama 3.2 3B | llama-3.2-3b | 128K | 32K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-10-03 Updated: 2026-01-28 |
| Venice Uncensored 1.1 | venice-uncensored | 32K | 8K | Input: $0.2 Output: $0.9 | Model: 0.100 Completion: 4.500 | 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2025-03-18 Updated: 2026-01-28 |
| GPT-5.2 Codex | openai-gpt-52-codex | 256K | 64K | Input: $2.19 Output: $17.5 Cache Read: $0.219 | Model: 1.095 Completion: 7.991 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image Out: text | Released: 2025-01-15 Updated: 2026-01-28 |
| Qwen3 VL 235B | qwen3-vl-235b-a22b | 256K | 64K | Input: $0.25 Output: $1.5 | Model: 0.125 Completion: 6.000 | 📎 🔧 🌡️ | - | In: text, image Out: text | Open Weights Released: 2026-01-16 Updated: 2026-01-28 |
| Claude Sonnet 4.5 | claude-sonnet-45 | 198K | 49.5K | Input: $3.75 Output: $18.75 Cache Read: $0.375 Cache Write: $4.69 | Model: 1.875 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-09 | In: text, image Out: text | Released: 2025-01-15 Updated: 2026-01-28 |
Vercel AI Gateway¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| INTELLECT 3 | prime-intellect/intellect-3 | 131.1K | 131.1K | Input: $0.2 Output: $1.1 | Model: 0.100 Completion: 5.500 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-11-26 |
| GLM-5 | zai/glm-5 | 202.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-12 Updated: 2026-02-19 |
| GLM 4.7 FlashX | zai/glm-4.7-flashx | 200K | 128K | Input: $0.06 Output: $0.4 Cache Read: $0.01 | Model: 0.030 Completion: 6.667 Cache: 0.167 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-01 |
| GLM 4.5 Air | zai/glm-4.5-air | 128K | 96K | Input: $0.2 Output: $1.1 | Model: 0.100 Completion: 5.500 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM 4.5 | zai/glm-4.5 | 131.1K | 131.1K | Input: $0.6 Output: $2.2 | Model: 0.300 Completion: 3.667 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM 4.6 | zai/glm-4.6 | 200K | 96K | Input: $0.45 Output: $1.8 | Model: 0.225 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM 4.7 | zai/glm-4.7 | 202.8K | 120K | Input: $0.43 Output: $1.75 Cache Read: $0.08 | Model: 0.215 Completion: 4.070 Cache: 0.186 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-12-22 |
| GLM-4.6V-Flash | zai/glm-4.6v-flash | 128K | 24K | - | - | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-09-30 |
| GLM 4.5V | zai/glm-4.5v | 66K | 66K | Input: $0.6 Output: $1.8 | Model: 0.300 Completion: 3.000 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image Out: text | Open Weights Released: 2025-08-11 |
| GLM-4.6V | zai/glm-4.6v | 128K | 24K | Input: $0.3 Output: $0.9 Cache Read: $0.05 | Model: 0.150 Completion: 3.000 Cache: 0.167 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-09-30 |
| Nvidia Nemotron Nano 12B V2 VL | nvidia/nemotron-nano-12b-v2-vl | 131.1K | 131.1K | Input: $0.2 Output: $0.6 | Model: 0.100 Completion: 3.000 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-12 |
| Nvidia Nemotron Nano 9B V2 | nvidia/nemotron-nano-9b-v2 | 131.1K | 131.1K | Input: $0.04 Output: $0.16 | Model: 0.020 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-08-18 |
| Nemotron 3 Nano 30B A3B | nvidia/nemotron-3-nano-30b-a3b | 262.1K | 262.1K | Input: $0.06 Output: $0.24 | Model: 0.030 Completion: 4.000 | 🧠 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12 |
| Trinity Large Preview | arcee-ai/trinity-large-preview | 131K | 131K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-01 |
| Trinity Mini | arcee-ai/trinity-mini | 131.1K | 131.1K | Input: $0.05 Output: $0.15 | Model: 0.025 Completion: 3.000 | 🌡️ | 2024-10 | In: text Out: text | Released: 2025-12 |
| MiMo V2 Flash | xiaomi/mimo-v2-flash | 262.1K | 32K | Input: $0.1 Output: $0.29 | Model: 0.050 Completion: 2.900 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-12-17 |
| Mercury Coder Small Beta | inception/mercury-coder-small | 32K | 16.4K | Input: $0.25 Output: $1 | Model: 0.125 Completion: 4.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-02-26 |
| voyage-3-large | voyage/voyage-3-large | 8.2K | 1.5K | Input: $0.18 Output: $0 | Model: 0.090 | - | - | In: text Out: text | Released: 2024-09 |
| voyage-code-3 | voyage/voyage-code-3 | 8.2K | 1.5K | Input: $0.18 Output: $0 | Model: 0.090 | - | - | In: text Out: text | Released: 2024-09 |
| voyage-law-2 | voyage/voyage-law-2 | 8.2K | 1.5K | Input: $0.12 Output: $0 | Model: 0.060 | - | - | In: text Out: text | Released: 2024-03 |
| voyage-finance-2 | voyage/voyage-finance-2 | 8.2K | 1.5K | Input: $0.12 Output: $0 | Model: 0.060 | - | - | In: text Out: text | Released: 2024-03 |
| voyage-code-2 | voyage/voyage-code-2 | 8.2K | 1.5K | Input: $0.12 Output: $0 | Model: 0.060 | - | - | In: text Out: text | Released: 2024-01 |
| voyage-3.5-lite | voyage/voyage-3.5-lite | 8.2K | 1.5K | Input: $0.02 Output: $0 | Model: 0.010 | - | - | In: text Out: text | Released: 2025-05-20 |
| voyage-3.5 | voyage/voyage-3.5 | 8.2K | 1.5K | Input: $0.06 Output: $0 | Model: 0.030 | - | - | In: text Out: text | Released: 2025-05-20 |
| Nova 2 Lite | amazon/nova-2-lite | 1M | 1M | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 📎 🧠 🌡️ | 2024-10 | In: text, image Out: text | Released: 2024-12-01 |
| Titan Text Embeddings V2 | amazon/titan-embed-text-v2 | 8.2K | 1.5K | Input: $0.02 Output: $0 | Model: 0.010 | - | - | In: text Out: text | Released: 2024-04 |
| Nova Lite | amazon/nova-lite | 300K | 8.2K | Input: $0.06 Output: $0.24 Cache Read: $0.015 | Model: 0.030 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Released: 2024-12-03 |
| Nova Pro | amazon/nova-pro | 300K | 8.2K | Input: $0.8 Output: $3.2 Cache Read: $0.2 | Model: 0.400 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-10 | In: text, image, video Out: text | Released: 2024-12-03 |
| Nova Micro | amazon/nova-micro | 128K | 8.2K | Input: $0.035 Output: $0.14 Cache Read: $0.00875 | Model: 0.018 Completion: 4.000 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12-03 |
| Qwen3 235B A22B Instruct 2507 | alibaba/qwen-3-235b | 41K | 16.4K | Input: $0.13 Output: $0.6 | Model: 0.065 Completion: 4.615 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04 |
| Qwen3 Max Preview | alibaba/qwen3-max-preview | 262.1K | 32.8K | Input: $1.2 Output: $6 Cache Read: $0.24 | Model: 0.600 Completion: 5.000 Cache: 0.200 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-09-23 |
| Qwen3 Next 80B A3B Thinking | alibaba/qwen3-next-80b-a3b-thinking | 131.1K | 65.5K | Input: $0.15 Output: $1.5 | Model: 0.075 Completion: 10.000 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Open Weights Released: 2025-09-12 |
| Qwen 3 Max Thinking | alibaba/qwen3-max-thinking | 256K | 65.5K | Input: $1.2 Output: $6 Cache Read: $0.24 | Model: 0.600 Completion: 5.000 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-01 | In: text Out: text | Open Weights Released: 2025-01 |
| Qwen3 VL Instruct | alibaba/qwen3-vl-instruct | 131.1K | 129K | Input: $0.7 Output: $2.8 | Model: 0.350 Completion: 4.000 | 📎 🔧 🌡️ | 2025-04 | In: text, image Out: text | Open Weights Released: 2025-09-24 |
| Qwen3 Embedding 8B | alibaba/qwen3-embedding-8b | 32.8K | 32.8K | Input: $0.05 Output: $0 | Model: 0.025 | - | - | In: text Out: text | Released: 2025-06-05 |
| Qwen3 Coder Next | alibaba/qwen3-coder-next | 256K | 256K | Input: $0.5 Output: $1.2 | Model: 0.250 Completion: 2.400 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2025-07-22 Updated: 2026-02-19 |
| Qwen3 Coder 480B A35B Instruct | alibaba/qwen3-coder | 262.1K | 66.5K | Input: $0.38 Output: $1.53 | Model: 0.190 Completion: 4.026 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04 |
| Qwen3-30B-A3B | alibaba/qwen-3-30b | 41K | 16.4K | Input: $0.08 Output: $0.29 | Model: 0.040 Completion: 3.625 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04 |
| Qwen3 Embedding 0.6B | alibaba/qwen3-embedding-0.6b | 32.8K | 32.8K | Input: $0.01 Output: $0 | Model: 0.005 | - | - | In: text Out: text | Released: 2025-11-14 |
| Qwen3-14B | alibaba/qwen-3-14b | 41K | 16.4K | Input: $0.06 Output: $0.24 | Model: 0.030 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04 |
| Qwen3 235B A22B Thinking 2507 | alibaba/qwen3-235b-a22b-thinking | 262.1K | 262.1K | Input: $0.3 Output: $2.9 | Model: 0.150 Completion: 9.667 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, pdf Out: text | Released: 2025-04 |
| Qwen3 VL Thinking | alibaba/qwen3-vl-thinking | 131.1K | 129K | Input: $0.7 Output: $8.4 | Model: 0.350 Completion: 12.000 | 📎 🧠 🔧 🌡️ | 2025-09 | In: text, image Out: text | Open Weights Released: 2025-09-24 |
| Qwen 3.5 Flash | alibaba/qwen3.5-flash | 1M | 64K | Input: $0.1 Output: $0.4 Cache Read: $0.001 Cache Write: $0.125 | Model: 0.050 Completion: 4.000 Cache: 0.010 | 📎 🧠 🔧 🌡️ | - | In: text, image, pdf Out: text | Released: 2026-02-24 |
| Qwen3 Next 80B A3B Instruct | alibaba/qwen3-next-80b-a3b-instruct | 262.1K | 32.8K | Input: $0.09 Output: $1.1 | Model: 0.045 Completion: 12.222 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-12 |
| Qwen 3.5 Plus | alibaba/qwen3.5-plus | 1M | 64K | Input: $0.4 Output: $2.4 Cache Read: $0.04 Cache Write: $0.5 | Model: 0.200 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, pdf Out: text | Released: 2026-02-16 Updated: 2026-02-19 |
| Qwen3 Max | alibaba/qwen3-max | 262.1K | 32.8K | Input: $1.2 Output: $6 | Model: 0.600 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-09-23 |
| Qwen 3.32B | alibaba/qwen-3-32b | 41K | 16.4K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04 |
| Qwen3 Coder Plus | alibaba/qwen3-coder-plus | 1M | 1M | Input: $1 Output: $5 | Model: 0.500 Completion: 5.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen3 Embedding 4B | alibaba/qwen3-embedding-4b | 32.8K | 32.8K | Input: $0.02 Output: $0 | Model: 0.010 | - | - | In: text Out: text | Released: 2025-06-05 |
| Qwen 3 Coder 30B A3B Instruct | alibaba/qwen3-coder-30b-a3b | 160K | 32.8K | Input: $0.07 Output: $0.27 | Model: 0.035 Completion: 3.857 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Released: 2025-04 |
| FLUX.1 Fill [pro] | bfl/flux-pro-1.0-fill | 512 | - | - | - | - | - | In: text Out: image | Released: 2024-10 |
| FLUX1.1 [pro] | bfl/flux-pro-1.1 | 512 | - | - | - | - | - | In: text Out: image | Released: 2024-10 |
| FLUX.1 Kontext Max | bfl/flux-kontext-max | 512 | - | - | - | - | - | In: text Out: image | Released: 2025-06 |
| FLUX.1 Kontext Pro | bfl/flux-kontext-pro | 512 | - | - | - | - | - | In: text Out: image | Released: 2025-06 |
| FLUX1.1 [pro] Ultra | bfl/flux-pro-1.1-ultra | 512 | - | - | - | - | - | In: text Out: image | Released: 2024-11 |
| Codestral Embed | mistral/codestral-embed | 8.2K | 1.5K | Input: $0.15 Output: $0 | Model: 0.075 | - | - | In: text Out: text | Released: 2025-05-28 |
| Devstral Small 2 | mistral/devstral-small-2 | 256K | 256K | - | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-05-07 |
| Devstral 2 | mistral/devstral-2 | 256K | 256K | - | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-12-09 |
| Mistral Large 3 | mistral/mistral-large-3 | 256K | 256K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 📎 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-12-02 |
| Mistral Embed | mistral/mistral-embed | 8.2K | 1.5K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Released: 2023-12-11 |
| Ministral 14B | mistral/ministral-14b | 256K | 256K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 📎 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-12-01 |
| Mistral Nemo | mistral/mistral-nemo | 60.3K | 16K | Input: $0.04 Output: $0.17 | Model: 0.020 Completion: 4.250 | 🔧 🌡️ | 2024-04 | In: text Out: text | Released: 2024-07-01 |
| Mistral Medium 3.1 | mistral/mistral-medium | 128K | 64K | Input: $0.4 Output: $2 | Model: 0.200 Completion: 5.000 | 📎 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-05-07 |
| Devstral Small 1.1 | mistral/devstral-small | 128K | 64K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-05-07 |
| Codestral | mistral/codestral | 256K | 4.1K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-05-29 Updated: 2025-01-04 |
| Mixtral 8x22B | mistral/mixtral-8x22b-instruct | 64K | 64K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 🔧 🌡️ | 2024-04 | In: text Out: text | Open Weights Released: 2024-04-17 |
| Mistral Small | mistral/mistral-small | 128K | 16.4K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-03 | In: text, image Out: text | Open Weights Released: 2024-09-01 Updated: 2024-09-04 |
| Ministral 8B | mistral/ministral-8b | 128K | 128K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-10-01 Updated: 2024-10-04 |
| Pixtral Large | mistral/pixtral-large | 128K | 128K | Input: $2 Output: $6 | Model: 1.000 Completion: 3.000 | 📎 🔧 🌡️ | 2024-11 | In: text, image Out: text | Open Weights Released: 2024-11-01 Updated: 2024-11-04 |
| Pixtral 12B | mistral/pixtral-12b | 128K | 128K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 📎 🔧 🌡️ | 2024-09 | In: text, image Out: text | Open Weights Released: 2024-09-01 |
| Magistral Small | mistral/magistral-small | 128K | 128K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-03-17 |
| Magistral Medium | mistral/magistral-medium | 128K | 16.4K | Input: $2 Output: $5 | Model: 1.000 Completion: 2.500 | 🧠 🔧 🌡️ | 2025-06 | In: text Out: text | Open Weights Released: 2025-03-17 Updated: 2025-03-20 |
| Ministral 3B | mistral/ministral-3b | 128K | 128K | Input: $0.04 Output: $0.04 | Model: 0.020 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-10-01 Updated: 2024-10-04 |
| KAT-Coder-Pro V1 | kwaipilot/kat-coder-pro-v1 | 256K | 32K | - | - | 🧠 🌡️ | 2024-10 | In: text Out: text | Released: 2025-10-24 |
| DeepSeek V3 0324 | deepseek/deepseek-v3 | 163.8K | 16.4K | Input: $0.77 Output: $0.77 | Model: 0.385 Completion: 1.000 | 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2024-12-26 |
| DeepSeek-V3.1 | deepseek/deepseek-v3.1 | 163.8K | 128K | Input: $0.3 Output: $1 | Model: 0.150 Completion: 3.333 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-08-21 |
| DeepSeek V3.1 Terminus | deepseek/deepseek-v3.1-terminus | 131.1K | 65.5K | Input: $0.27 Output: $1 | Model: 0.135 Completion: 3.704 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Open Weights Released: 2025-09-22 |
| DeepSeek V3.2 | deepseek/deepseek-v3.2 | 163.8K | 8K | Input: $0.27 Output: $0.4 Cache Read: $0.22 | Model: 0.135 Completion: 1.481 Cache: 0.815 | 🌡️ | 2024-07 | In: text Out: text | Released: 2025-12-01 |
| DeepSeek V3.2 Thinking | deepseek/deepseek-v3.2-thinking | 128K | 64K | Input: $0.28 Output: $0.42 Cache Read: $0.03 | Model: 0.140 Completion: 1.500 Cache: 0.107 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-12-01 |
| DeepSeek V3.2 Exp | deepseek/deepseek-v3.2-exp | 163.8K | 163.8K | Input: $0.27 Output: $0.4 | Model: 0.135 Completion: 1.481 | 🧠 🔧 🌡️ | 2025-09 | In: text Out: text | Released: 2025-09-29 |
| DeepSeek-R1 | deepseek/deepseek-r1 | 128K | 32.8K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Released: 2025-01-20 Updated: 2025-05-29 |
| Kimi K2 Turbo | moonshotai/kimi-k2-turbo | 256K | 16.4K | Input: $2.4 Output: $10 | Model: 1.200 Completion: 4.167 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2025-09-05 |
| Kimi K2 0905 | moonshotai/kimi-k2-0905 | 131.1K | 16.4K | Input: $0.6 Output: $2.5 | Model: 0.300 Completion: 4.167 | 🌡️ | 2024-10 | In: text Out: text | Released: 2025-09-05 |
| Kimi K2.5 | moonshotai/kimi-k2.5 | 262.1K | 262.1K | Input: $0.6 Output: $1.2 | Model: 0.300 Completion: 2.000 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video Out: text | Open Weights Released: 2026-01-26 |
| Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 216.1K | 216.1K | Input: $0.47 Output: $2 Cache Read: $0.14 | Model: 0.235 Completion: 4.255 Cache: 0.298 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2025-11-06 |
| Kimi K2 Thinking Turbo | moonshotai/kimi-k2-thinking-turbo | 262.1K | 262.1K | Input: $1.15 Output: $8 Cache Read: $0.15 | Model: 0.575 Completion: 6.957 Cache: 0.130 | 🧠 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2025-11-06 |
| Kimi K2 Instruct | moonshotai/kimi-k2 | 131.1K | 16.4K | Input: $1 Output: $3 | Model: 0.500 Completion: 3.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-14 |
| Gemini Embedding 001 | google/gemini-embedding-001 | 8.2K | 1.5K | Input: $0.15 Output: $0 | Model: 0.075 | - | - | In: text Out: text | Released: 2025-05-20 |
| Gemini 2.5 Flash Lite Preview 09-25 | google/gemini-2.5-flash-lite-preview-09-2025 | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.01 | Model: 0.050 Completion: 4.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Imagen 4 Fast | google/imagen-4.0-fast-generate-001 | 480 | - | - | - | - | - | In: text Out: image | Released: 2025-06 |
| Text Embedding 005 | google/text-embedding-005 | 8.2K | 1.5K | Input: $0.03 Output: $0 | Model: 0.015 | - | - | In: text Out: text | Released: 2024-08 |
| Gemini 2.5 Flash Preview 09-25 | google/gemini-2.5-flash-preview-09-2025 | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.03 Cache Write: $0.383 | Model: 0.150 Completion: 8.333 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-09-25 |
| Gemini 3 Flash | google/gemini-3-flash | 1M | 64K | Input: $0.5 Output: $3 Cache Read: $0.05 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03 | In: text, image, pdf Out: text | Released: 2025-12-17 |
| Imagen 4 Ultra | google/imagen-4.0-ultra-generate-001 | 480 | - | - | - | - | - | In: text Out: image | Released: 2025-05-24 |
| Text Multilingual Embedding 002 | google/text-multilingual-embedding-002 | 8.2K | 1.5K | Input: $0.03 Output: $0 | Model: 0.015 | - | - | In: text Out: text | Released: 2024-03 |
| Gemini 2.5 Flash Lite | google/gemini-2.5-flash-lite | 1M | 65.5K | Input: $0.1 Output: $0.4 Cache Read: $0.01 | Model: 0.050 Completion: 4.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-06-17 |
| Gemini 3.1 Pro Preview | google/gemini-3.1-pro-preview | 1M | 64K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, pdf Out: text | Released: 2026-02-19 Updated: 2026-02-24 |
| Nano Banana (Gemini 2.5 Flash Image) | google/gemini-2.5-flash-image | 32.8K | 32.8K | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 🌡️ | 2025-01 | In: text Out: text, image | Released: 2025-03-20 |
| Nano Banana Pro (Gemini 3 Pro Image) | google/gemini-3-pro-image | 65.5K | 32.8K | Input: $2 Output: $120 | Model: 1.000 Completion: 60.000 | 🌡️ | 2025-03 | In: text Out: text, image | Released: 2025-09 |
| Nano Banana Preview (Gemini 2.5 Flash Image Preview) | google/gemini-2.5-flash-image-preview | 32.8K | 32.8K | Input: $0.3 Output: $2.5 | Model: 0.150 Completion: 8.333 | 🌡️ | 2025-01 | In: text Out: text, image | Released: 2025-03-20 |
| Imagen 4 | google/imagen-4.0-generate-001 | 480 | - | - | - | - | - | In: text Out: image | Released: 2025-05-22 |
| Gemini 3 Pro Preview | google/gemini-3-pro-preview | 1M | 64K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-11-18 |
| Gemini 2.0 Flash | google/gemini-2.0-flash | 1M | 8.2K | Input: $0.1 Output: $0.4 Cache Read: $0.025 | Model: 0.050 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-06 | In: text, image, audio, video, pdf Out: text | Released: 2024-12-11 |
| Gemini 2.5 Pro | google/gemini-2.5-pro | 1M | 65.5K | Input: $1.25 Output: $10 Cache Read: $0.31 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| Gemini 2.0 Flash Lite | google/gemini-2.0-flash-lite | 1M | 8.2K | Input: $0.075 Output: $0.3 | Model: 0.037 Completion: 4.000 | 📎 🔧 🌡️ | 2024-06 | In: text, image, audio, video, pdf Out: text | Released: 2024-12-11 |
| Gemini 2.5 Flash | google/gemini-2.5-flash | 1M | 65.5K | Input: $0.3 Output: $2.5 Cache Read: $0.075 Input Audio: $1 | Model: 0.500 Completion: 2.500 Cache: 0.075 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, audio, video, pdf Out: text | Released: 2025-03-20 Updated: 2025-06-05 |
| LongCat Flash Thinking | meituan/longcat-flash-thinking | 128K | 8.2K | Input: $0.15 Output: $1.5 | Model: 0.075 Completion: 10.000 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-09-23 |
| LongCat Flash Chat | meituan/longcat-flash-chat | 128K | 8.2K | - | - | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-08-30 |
| Seed 1.6 | bytedance/seed-1.6 | 256K | 32K | Input: $0.25 Output: $2 Cache Read: $0.05 | Model: 0.125 Completion: 8.000 Cache: 0.200 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-09 |
| Seed 1.8 | bytedance/seed-1.8 | 256K | 64K | Input: $0.25 Output: $2 Cache Read: $0.05 | Model: 0.125 Completion: 8.000 Cache: 0.200 | 🧠 🔧 🌡️ | 2024-10 | In: text, image Out: text | Released: 2025-10 |
| Llama 3.1 8B Instruct | meta/llama-3.1-8b | 131.1K | 16.4K | Input: $0.03 Output: $0.05 | Model: 0.015 Completion: 1.667 | 🔧 🌡️ | 2023-12 | In: text Out: text | Released: 2024-07-23 |
| Llama 3.2 11B Vision Instruct | meta/llama-3.2-11b | 128K | 8.2K | Input: $0.16 Output: $0.16 | Model: 0.080 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Released: 2024-09-25 |
| Llama 3.1 70B Instruct | meta/llama-3.1-70b | 131.1K | 16.4K | Input: $0.4 Output: $0.4 | Model: 0.200 Completion: 1.000 | 🔧 🌡️ | 2023-12 | In: text Out: text | Released: 2024-07-23 |
| Llama 3.2 90B Vision Instruct | meta/llama-3.2-90b | 128K | 8.2K | Input: $0.72 Output: $0.72 | Model: 0.360 Completion: 1.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Released: 2024-09-25 |
| Llama 3.2 1B Instruct | meta/llama-3.2-1b | 128K | 8.2K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🌡️ | 2023-12 | In: text Out: text | Released: 2024-09-18 |
| Llama 3.2 3B Instruct | meta/llama-3.2-3b | 128K | 8.2K | Input: $0.15 Output: $0.15 | Model: 0.075 Completion: 1.000 | 🌡️ | 2023-12 | In: text Out: text | Released: 2024-09-18 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | meta/llama-4-maverick | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| Llama-3.3-70B-Instruct | meta/llama-3.3-70b | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Llama-4-Scout-17B-16E-Instruct-FP8 | meta/llama-4-scout | 128K | 4.1K | Input: $0 Output: $0 | - | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Open Weights Released: 2025-04-05 |
| v0-1.5-md | vercel/v0-1.5-md | 128K | 32K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-06-09 |
| v0-1.0-md | vercel/v0-1.0-md | 128K | 32K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🧠 🔧 🌡️ | - | In: text, image Out: text | Released: 2025-05-22 |
| GPT 5.3 Codex | openai/gpt-5.3-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | - | In: text, image, pdf Out: text | Released: 2026-02-24 |
| GPT-5 pro | openai/gpt-5-pro | 400K | 272K | Input: $15 Output: $120 | Model: 7.500 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text, image | Released: 2025-08-07 |
| text-embedding-ada-002 | openai/text-embedding-ada-002 | 8.2K | 1.5K | Input: $0.1 Output: $0 | Model: 0.050 | - | - | In: text Out: text | Released: 2022-12-15 |
| GPT 4o Mini Search Preview | openai/gpt-4o-mini-search-preview | 128K | 16.4K | Input: $0.15 Output: $0.6 | Model: 0.075 Completion: 4.000 | 🌡️ | 2023-09 | In: text Out: text | Released: 2025-01 |
| GPT 5.1 Codex Max | openai/gpt-5.1-codex-max | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-08-07 |
| GPT-5.2-Codex | openai/gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-12 |
| o3-deep-research | openai/o3-deep-research | 200K | 100K | Input: $10 Output: $40 Cache Read: $2.5 | Model: 5.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-10 | In: text, image, pdf Out: text | Released: 2024-06-26 |
| GPT-5.2 Chat | openai/gpt-5.2-chat | 128K | 16.4K | Input: $1.75 Output: $14 Cache Read: $0.18 | Model: 0.875 Completion: 8.000 Cache: 0.103 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-08-07 |
| GPT-5 Chat | openai/gpt-5-chat | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text, image | Released: 2025-08-07 |
| text-embedding-3-small | openai/text-embedding-3-small | 8.2K | 1.5K | Input: $0.02 Output: $0 | Model: 0.010 | - | - | In: text Out: text | Released: 2024-01-25 |
| text-embedding-3-large | openai/text-embedding-3-large | 8.2K | 1.5K | Input: $0.13 Output: $0 | Model: 0.065 | - | - | In: text Out: text | Released: 2024-01-25 |
| GPT-3.5 Turbo | openai/gpt-3.5-turbo | 16.4K | 4.1K | Input: $0.5 Output: $1.5 | Model: 0.250 Completion: 3.000 | 🌡️ | 2021-09 | In: text Out: text | Released: 2023-03-01 |
| GPT OSS 120B | openai/gpt-oss-120b | 131.1K | 131.1K | Input: $0.1 Output: $0.5 | Model: 0.050 Completion: 5.000 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT-5.1 Codex mini | openai/gpt-5.1-codex-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-05-16 |
| GPT-5.2 | openai/gpt-5.2 | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.18 | Model: 0.875 Completion: 8.000 Cache: 0.103 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-08-07 |
| o3 Pro | openai/o3-pro | 200K | 100K | Input: $20 Output: $80 | Model: 10.000 Completion: 4.000 | 📎 🧠 🔧 | 2024-10 | In: text, image, pdf Out: text | Released: 2025-04-16 |
| GPT 5.1 Thinking | openai/gpt-5.1-thinking | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 | 2024-10 | In: text, image, pdf Out: text, image | Released: 2025-08-07 |
| Codex Mini | openai/codex-mini | 200K | 100K | Input: $1.5 Output: $6 Cache Read: $0.38 | Model: 0.750 Completion: 4.000 Cache: 0.253 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-05-16 |
| gpt-oss-safeguard-20b | openai/gpt-oss-safeguard-20b | 131.1K | 65.5K | Input: $0.08 Output: $0.3 Cache Read: $0.04 | Model: 0.040 Completion: 3.750 Cache: 0.500 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2024-12-01 |
| GPT-5.1-Codex | openai/gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-08-07 |
| **GPT 5.2 ** | openai/gpt-5.2-pro | 400K | 128K | Input: $21 Output: $168 | Model: 10.500 Completion: 8.000 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text | Released: 2025-08-07 |
| GPT OSS 20B | openai/gpt-oss-20b | 131.1K | 32.8K | Input: $0.07 Output: $0.3 | Model: 0.035 Completion: 4.286 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-08-05 |
| GPT-3.5 Turbo Instruct | openai/gpt-3.5-turbo-instruct | 8.2K | 4.1K | Input: $1.5 Output: $2 | Model: 0.750 Completion: 1.333 | 🌡️ | 2021-09 | In: text Out: text | Released: 2023-03-01 |
| GPT-5.1 Instant | openai/gpt-5.1-instant | 128K | 16.4K | Input: $1.25 Output: $10 Cache Read: $0.13 | Model: 0.625 Completion: 8.000 Cache: 0.104 | 📎 🧠 🔧 🌡️ | 2024-10 | In: text, image, pdf Out: text, image | Released: 2025-08-07 |
| GPT-4o | openai/gpt-4o | 128K | 16.4K | Input: $2.5 Output: $10 Cache Read: $1.25 | Model: 1.250 Completion: 4.000 Cache: 0.500 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-05-13 Updated: 2024-08-06 |
| GPT-5 Nano | openai/gpt-5-nano | 400K | 128K | Input: $0.05 Output: $0.4 Cache Read: $0.005 | Model: 0.025 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-5 Mini | openai/gpt-5-mini | 400K | 128K | Input: $0.25 Output: $2 Cache Read: $0.025 | Model: 0.125 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
| o3-mini | openai/o3-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.55 | Model: 0.550 Completion: 4.000 Cache: 0.500 | 🧠 🔧 | 2024-05 | In: text Out: text | Released: 2024-12-20 Updated: 2025-01-29 |
| GPT-4.1 mini | openai/gpt-4.1-mini | 1M | 32.8K | Input: $0.4 Output: $1.6 Cache Read: $0.1 | Model: 0.200 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| o4-mini | openai/o4-mini | 200K | 100K | Input: $1.1 Output: $4.4 Cache Read: $0.28 | Model: 0.550 Completion: 4.000 Cache: 0.255 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| GPT-5 | openai/gpt-5 | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 📎 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-08-07 |
| GPT-4 Turbo | openai/gpt-4-turbo | 128K | 4.1K | Input: $10 Output: $30 | Model: 5.000 Completion: 3.000 | 📎 🔧 🌡️ | 2023-12 | In: text, image Out: text | Released: 2023-11-06 Updated: 2024-04-09 |
| GPT-4.1 | openai/gpt-4.1 | 1M | 32.8K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| GPT-4.1 nano | openai/gpt-4.1-nano | 1M | 32.8K | Input: $0.1 Output: $0.4 Cache Read: $0.03 | Model: 0.050 Completion: 4.000 Cache: 0.300 | 📎 🔧 🌡️ | 2024-04 | In: text, image Out: text | Released: 2025-04-14 |
| o3 | openai/o3 | 200K | 100K | Input: $2 Output: $8 Cache Read: $0.5 | Model: 1.000 Completion: 4.000 Cache: 0.250 | 📎 🧠 🔧 | 2024-05 | In: text, image Out: text | Released: 2025-04-16 |
| o1 | openai/o1 | 200K | 100K | Input: $15 Output: $60 Cache Read: $7.5 | Model: 7.500 Completion: 4.000 Cache: 0.500 | 📎 🧠 🔧 | 2023-09 | In: text, image Out: text | Released: 2024-12-05 |
| GPT-4o mini | openai/gpt-4o-mini | 128K | 16.4K | Input: $0.15 Output: $0.6 Cache Read: $0.08 | Model: 0.075 Completion: 4.000 Cache: 0.533 | 📎 🔧 🌡️ | 2023-09 | In: text, image Out: text | Released: 2024-07-18 |
| GPT-5-Codex | openai/gpt-5-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-09-15 |
| Morph v3 Large | morph/morph-v3-large | 32K | 32K | Input: $0.9 Output: $1.9 | Model: 0.450 Completion: 2.111 | - | - | In: text Out: text | Released: 2024-08-15 |
| Morph v3 Fast | morph/morph-v3-fast | 16K | 16K | Input: $0.8 Output: $1.2 | Model: 0.400 Completion: 1.500 | - | - | In: text Out: text | Released: 2024-08-15 |
| Embed v4.0 | cohere/embed-v4.0 | 8.2K | 1.5K | Input: $0.12 Output: $0 | Model: 0.060 | - | - | In: text Out: text | Released: 2025-04-15 |
| Command A | cohere/command-a | 256K | 8K | Input: $2.5 Output: $10 | Model: 1.250 Completion: 4.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-03-13 |
| MiniMax M2.1 Lightning | minimax/minimax-m2.1-lightning | 204.8K | 131.1K | Input: $0.3 Output: $2.4 Cache Read: $0.03 Cache Write: $0.38 | Model: 0.150 Completion: 8.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-10-27 |
| MiniMax M2.1 | minimax/minimax-m2.1 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.38 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-10-27 |
| MiniMax M2 | minimax/minimax-m2 | 262.1K | 262.1K | Input: $0.27 Output: $1.15 Cache Read: $0.03 Cache Write: $0.38 | Model: 0.135 Completion: 4.259 Cache: 0.111 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-10-27 |
| MiniMax M2.5 | minimax/minimax-m2.5 | 204.8K | 131K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.375 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-12 Updated: 2026-02-19 |
| Recraft V2 | recraft/recraft-v2 | 512 | - | - | - | - | - | In: text Out: image | Released: 2024-03 |
| Recraft V3 | recraft/recraft-v3 | 512 | - | - | - | - | - | In: text Out: image | Released: 2024-10 |
| Sonar Reasoning Pro | perplexity/sonar-reasoning-pro | 127K | 8K | Input: $2 Output: $8 | Model: 1.000 Completion: 4.000 | 🧠 🌡️ | 2025-09 | In: text Out: text | Released: 2025-02-19 |
| Sonar | perplexity/sonar | 127K | 8K | Input: $1 Output: $1 | Model: 0.500 Completion: 1.000 | 📎 🔧 🌡️ | 2025-02 | In: text, image Out: text | Released: 2025-02-19 |
| Sonar Reasoning | perplexity/sonar-reasoning | 127K | 8K | Input: $1 Output: $5 | Model: 0.500 Completion: 5.000 | 🧠 🌡️ | 2025-09 | In: text Out: text | Released: 2025-02-19 |
| Sonar Pro | perplexity/sonar-pro | 200K | 8K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🔧 🌡️ | 2025-09 | In: text, image Out: text | Released: 2025-02-19 |
| Claude Sonnet 4.6 | anthropic/claude-sonnet-4.6 | 1M | 128K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-08 | In: text, image, pdf Out: text | Released: 2026-02-17 |
| Claude Haiku 4.5 | anthropic/claude-haiku-4.5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-02-28 | In: text, image, pdf Out: text | Released: 2025-10-15 |
| Claude Opus 4.5 | anthropic/claude-opus-4.5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $18.75 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-11-24 |
| Claude 3.5 Sonnet (2024-06-20) | anthropic/claude-3.5-sonnet-20240620 | 200K | 8.2K | Input: $3 Output: $15 | Model: 1.500 Completion: 5.000 | 📎 🔧 🌡️ | 2024-04 | In: text, image, pdf Out: text | Released: 2024-06-20 |
| Claude Opus 4.6 | anthropic/claude-opus-4.6 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-05 | In: text, image, pdf Out: text | Released: 2026-02 |
| Claude Sonnet 4.5 | anthropic/claude-sonnet-4.5 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-07-31 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Claude Sonnet 4 | anthropic/claude-sonnet-4 | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Opus 3 | anthropic/claude-3-opus | 200K | 4.1K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-02-29 |
| Claude Opus 4 | anthropic/claude-opus-4 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Haiku 3.5 | anthropic/claude-3.5-haiku | 200K | 8.2K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-07-31 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude Haiku 3 | anthropic/claude-3-haiku | 200K | 4.1K | Input: $0.25 Output: $1.25 Cache Read: $0.03 Cache Write: $0.3 | Model: 0.125 Completion: 5.000 Cache: 0.120 | 📎 🔧 🌡️ | 2023-08-31 | In: text, image, pdf Out: text | Released: 2024-03-13 |
| Claude Opus 4 | anthropic/claude-opus-4.1 | 200K | 32K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-03-31 | In: text, image, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 3.7 | anthropic/claude-3.7-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2024-10-31 | In: text, image, pdf Out: text | Released: 2025-02-19 |
| Claude Sonnet 3.5 v2 | anthropic/claude-3.5-sonnet | 200K | 8.2K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2024-04-30 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Grok 4 Fast Reasoning | xai/grok-4-fast-reasoning | 2M | 256K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-07-09 |
| Grok Imagine Image | xai/grok-imagine-image | - | - | - | - | 🌡️ | - | In: text Out: text, image | Released: 2026-01-28 Updated: 2026-02-19 |
| Grok 4.1 Fast Reasoning | xai/grok-4.1-fast-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-07-09 |
| Grok 4.1 Fast Non-Reasoning | xai/grok-4.1-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 🔧 🌡️ | 2024-10 | In: text Out: text | Released: 2025-07-09 |
| Grok Imagine Image Pro | xai/grok-imagine-image-pro | - | - | - | - | 🌡️ | - | In: text Out: text, image | Released: 2026-01-28 Updated: 2026-02-19 |
| Grok 3 Fast | xai/grok-3-fast | 131.1K | 8.2K | Input: $5 Output: $25 Cache Read: $1.25 | Model: 2.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 4 Fast (Non-Reasoning) | xai/grok-4-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-09-19 |
| Grok 3 Mini | xai/grok-3-mini | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 Reasoning: $0.5 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 4 | xai/grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 Reasoning: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-09 |
| Grok 3 Mini Fast | xai/grok-3-mini-fast | 131.1K | 8.2K | Input: $0.6 Output: $4 Cache Read: $0.15 Reasoning: $4 | Model: 0.300 Completion: 6.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok Code Fast 1 | xai/grok-code-fast-1 | 256K | 10K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Released: 2025-08-28 |
| Grok 3 | xai/grok-3 | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 2 Vision | xai/grok-2-vision | 8.2K | 4.1K | Input: $2 Output: $10 Cache Read: $2 | Model: 1.000 Completion: 5.000 Cache: 1.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Released: 2024-08-20 |
Vivgrid¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5 | glm-5 | 202.8K | 131K | Input: $1 Output: $3.2 Cache Read: $0.2 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Open Weights Released: 2026-02-12 |
| GPT-5.1 Codex Max | gpt-5.1-codex-max | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| GPT-5.2 Codex | gpt-5.2-codex | 400K | 128K | Input: $1.75 Output: $14 Cache Read: $0.175 | Model: 0.875 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2025-08-31 | In: text, image Out: text | Released: 2026-01-14 |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 1M | 65.5K | Input: $0.5 Output: $3 Cache Read: $0.05 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-12-17 |
| DeepSeek-V3.2 | deepseek-v3.2 | 128K | 128K | Input: $0.28 Output: $0.42 | Model: 0.140 Completion: 1.500 | 🧠 🔧 🌡️ | 2024-07 | In: text Out: text | Open Weights Released: 2025-12-01 |
| GPT-5.1 Codex | gpt-5.1-codex | 400K | 128K | Input: $1.25 Output: $10 Cache Read: $0.125 | Model: 0.625 Completion: 8.000 Cache: 0.100 | 🧠 🔧 | 2024-09-30 | In: text, image Out: text | Released: 2025-11-13 |
| Gemini 3 Pro Preview | gemini-3-pro-preview | 1M | 65.5K | Input: $2 Output: $12 Cache Read: $0.2 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01 | In: text, image, video, audio, pdf Out: text | Released: 2025-11-18 |
| GPT-5 Mini | gpt-5-mini | 272K | 128K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 | 2024-05-30 | In: text, image Out: text | Released: 2025-08-07 |
Vultr¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2 Instruct | kimi-k2-instruct | 58.9K | 4.1K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-07-18 |
| Qwen2.5 Coder 32B Instruct | qwen2.5-coder-32b-instruct | 13K | 2K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2024-11-06 |
| GPT OSS 120B | gpt-oss-120b | 121.8K | 8.2K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-06-23 |
| DeepSeek R1 Distill Llama 70B | deepseek-r1-distill-llama-70b | 121.8K | 8.2K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-01-20 |
| DeepSeek R1 Distill Qwen 32B | deepseek-r1-distill-qwen-32b | 121.8K | 8.2K | Input: $0.2 Output: $0.2 | Model: 0.100 Completion: 1.000 | 🧠 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-01-20 |
Weights & Biases¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Phi-4-mini-instruct | microsoft/Phi-4-mini-instruct | 128K | 4.1K | Input: $0.08 Output: $0.35 | Model: 0.040 Completion: 4.375 | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Open Weights Released: 2024-12-11 |
| DeepSeek-R1-0528 | deepseek-ai/DeepSeek-R1-0528 | 161K | 163.8K | Input: $1.35 Output: $5.4 | Model: 0.675 Completion: 4.000 | 🧠 🔧 🌡️ | 2025-05 | In: text Out: text | Open Weights Released: 2025-05-28 |
| DeepSeek-V3-0324 | deepseek-ai/DeepSeek-V3-0324 | 161K | 8.2K | Input: $1.14 Output: $2.75 | Model: 0.570 Completion: 2.412 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-03-24 |
| Kimi-K2-Instruct | moonshotai/Kimi-K2-Instruct | 128K | 16.4K | Input: $1.35 Output: $4 | Model: 0.675 Completion: 2.963 | 🔧 🌡️ | 2024-10 | In: text Out: text | Open Weights Released: 2025-07-14 |
| Llama 4 Scout 17B 16E Instruct | meta-llama/Llama-4-Scout-17B-16E-Instruct | 64K | 8.2K | Input: $0.17 Output: $0.66 | Model: 0.085 Completion: 3.882 | 🧠 🔧 🌡️ | 2024-12 | In: text, image Out: text | Open Weights Released: 2025-01-31 |
| Meta-Llama-3.1-8B-Instruct | meta-llama/Llama-3.1-8B-Instruct | 128K | 32.8K | Input: $0.22 Output: $0.22 | Model: 0.110 Completion: 1.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-07-23 |
| Llama-3.3-70B-Instruct | meta-llama/Llama-3.3-70B-Instruct | 128K | 32.8K | Input: $0.71 Output: $0.71 | Model: 0.355 Completion: 1.000 | 🧠 🔧 🌡️ | 2023-12 | In: text Out: text | Open Weights Released: 2024-12-06 |
| Qwen3-235B-A22B-Thinking-2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262.1K | 131.1K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-25 |
| Qwen3-Coder-480B-A35B-Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct | 262.1K | 66.5K | Input: $1 Output: $1.5 | Model: 0.500 Completion: 1.500 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-23 |
| Qwen3 235B A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262.1K | 131.1K | Input: $0.1 Output: $0.1 | Model: 0.050 Completion: 1.000 | 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-04-28 Updated: 2025-07-21 |
xAI¶
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| Grok 2 (1212) | grok-2-1212 | 131.1K | 8.2K | Input: $2 Output: $10 Cache Read: $2 | Model: 1.000 Completion: 5.000 Cache: 1.000 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-12-12 |
| Grok 2 | grok-2 | 131.1K | 8.2K | Input: $2 Output: $10 Cache Read: $2 | Model: 1.000 Completion: 5.000 Cache: 1.000 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-08-20 |
| Grok 3 Fast Latest | grok-3-fast-latest | 131.1K | 8.2K | Input: $5 Output: $25 Cache Read: $1.25 | Model: 2.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 2 Vision | grok-2-vision | 8.2K | 4.1K | Input: $2 Output: $10 Cache Read: $2 | Model: 1.000 Completion: 5.000 Cache: 1.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Released: 2024-08-20 |
| Grok 3 | grok-3 | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok Code Fast 1 | grok-code-fast-1 | 256K | 10K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🧠 🔧 🌡️ | 2023-10 | In: text Out: text | Released: 2025-08-28 |
| Grok 2 Vision (1212) | grok-2-vision-1212 | 8.2K | 4.1K | Input: $2 Output: $10 Cache Read: $2 | Model: 1.000 Completion: 5.000 Cache: 1.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Released: 2024-08-20 Updated: 2024-12-12 |
| Grok 4.1 Fast (Non-Reasoning) | grok-4-1-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-11-19 |
| Grok Beta | grok-beta | 131.1K | 4.1K | Input: $5 Output: $15 Cache Read: $5 | Model: 2.500 Completion: 3.000 Cache: 1.000 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-11-01 |
| Grok 3 Mini Fast | grok-3-mini-fast | 131.1K | 8.2K | Input: $0.6 Output: $4 Cache Read: $0.15 Reasoning: $4 | Model: 0.300 Completion: 6.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 4 Fast | grok-4-fast | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-09-19 |
| Grok 4 | grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 Reasoning: $15 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-07 | In: text Out: text | Released: 2025-07-09 |
| Grok 3 Latest | grok-3-latest | 131.1K | 8.2K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 4.1 Fast | grok-4-1-fast | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-11-19 |
| Grok 2 Vision Latest | grok-2-vision-latest | 8.2K | 4.1K | Input: $2 Output: $10 Cache Read: $2 | Model: 1.000 Completion: 5.000 Cache: 1.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Released: 2024-08-20 Updated: 2024-12-12 |
| Grok 3 Mini Latest | grok-3-mini-latest | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 Reasoning: $0.5 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 3 Mini | grok-3-mini | 131.1K | 8.2K | Input: $0.3 Output: $0.5 Cache Read: $0.075 Reasoning: $0.5 | Model: 0.150 Completion: 1.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 3 Mini Fast Latest | grok-3-mini-fast-latest | 131.1K | 8.2K | Input: $0.6 Output: $4 Cache Read: $0.15 Reasoning: $4 | Model: 0.300 Completion: 6.667 Cache: 0.250 | 🧠 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
| Grok 2 Latest | grok-2-latest | 131.1K | 8.2K | Input: $2 Output: $10 Cache Read: $2 | Model: 1.000 Completion: 5.000 Cache: 1.000 | 🔧 🌡️ | 2024-08 | In: text Out: text | Released: 2024-08-20 Updated: 2024-12-12 |
| Grok 4 Fast (Non-Reasoning) | grok-4-fast-non-reasoning | 2M | 30K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🔧 🌡️ | 2025-07 | In: text, image Out: text | Released: 2025-09-19 |
| Grok Vision Beta | grok-vision-beta | 8.2K | 4.1K | Input: $5 Output: $15 Cache Read: $5 | Model: 2.500 Completion: 3.000 Cache: 1.000 | 📎 🔧 🌡️ | 2024-08 | In: text, image Out: text | Released: 2024-11-01 |
| Grok 3 Fast | grok-3-fast | 131.1K | 8.2K | Input: $5 Output: $25 Cache Read: $1.25 | Model: 2.500 Completion: 5.000 Cache: 0.250 | 🔧 🌡️ | 2024-11 | In: text Out: text | Released: 2025-02-17 |
Xiaomi¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| MiMo-V2-Flash | mimo-v2-flash | 256K | 32K | Input: $0.07 Output: $0.21 | Model: 0.035 Completion: 3.000 | 🧠 🔧 🌡️ | 2024-12-01 | In: text Out: text | Open Weights Released: 2025-12-17 |
Z.AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5 | glm-5 | 204.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.2 Cache Write: $0 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-11 |
| GLM-4.5-Air | glm-4.5-air | 131.1K | 98.3K | Input: $0.2 Output: $1.1 Cache Read: $0.03 Cache Write: $0 | Model: 0.100 Completion: 5.500 Cache: 0.150 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5 | glm-4.5 | 131.1K | 98.3K | Input: $0.6 Output: $2.2 Cache Read: $0.11 Cache Write: $0 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5-Flash | glm-4.5-flash | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.7-Flash | glm-4.7-flash | 200K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-01-19 |
| GLM-4.6 | glm-4.6 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.11 Cache Write: $0 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7 | glm-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.11 Cache Write: $0 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-4.5V | glm-4.5v | 64K | 16.4K | Input: $0.6 Output: $1.8 | Model: 0.300 Completion: 3.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-08-11 |
| GLM-4.6V | glm-4.6v | 128K | 32.8K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-12-08 |
Z.AI Coding Plan¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5 | glm-5 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-11 |
| GLM-4.7-FlashX | glm-4.7-flashx | 200K | 131.1K | Input: $0.07 Output: $0.4 Cache Read: $0.01 Cache Write: $0 | Model: 0.035 Completion: 5.714 Cache: 0.143 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-01-19 |
| GLM-4.5-Air | glm-4.5-air | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5 | glm-4.5 | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5-Flash | glm-4.5-flash | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.7-Flash | glm-4.7-flash | 200K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-01-19 |
| GLM-4.6 | glm-4.6 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7 | glm-4.7 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-4.5V | glm-4.5v | 64K | 16.4K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-08-11 |
| GLM-4.6V | glm-4.6v | 128K | 32.8K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-12-08 |
ZenMux¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| MiMo-V2-Flash Free | xiaomi/mimo-v2-flash-free | 262K | 64K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-12-17 |
| MiMo-V2-Flash | xiaomi/mimo-v2-flash | 262K | 64K | Input: $0.1 Output: $0.3 Cache Read: $0.01 | Model: 0.050 Completion: 3.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-12-17 |
| KAT-Coder-Pro-V1 Free | kuaishou/kat-coder-pro-v1-free | 256K | 64K | Input: $0 Output: $0 | - | 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-10-23 |
| KAT-Coder-Pro-V1 | kuaishou/kat-coder-pro-v1 | 256K | 64K | Input: $0.3 Output: $1.2 Cache Read: $0.06 | Model: 0.150 Completion: 4.000 Cache: 0.200 | 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-10-23 |
| Step 3.5 Flash (Free) | stepfun/step-3.5-flash-free | 256K | 64K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-02-02 |
| Step 3.5 Flash | stepfun/step-3.5-flash | 256K | 64K | Input: $0.1 Output: $0.3 | Model: 0.050 Completion: 3.000 | 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-02-02 |
| Step-3 | stepfun/step-3 | 65.5K | 64K | Input: $0.21 Output: $0.57 | Model: 0.105 Completion: 2.714 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text Out: text | Released: 2025-07-31 |
| Ling-1T | inclusionai/ling-1t | 128K | 64K | Input: $0.56 Output: $2.24 Cache Read: $0.11 | Model: 0.280 Completion: 4.000 Cache: 0.196 | 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-10-09 |
| Ring-1T | inclusionai/ring-1t | 128K | 64K | Input: $0.56 Output: $2.24 Cache Read: $0.11 | Model: 0.280 Completion: 4.000 Cache: 0.196 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-10-12 |
| Doubao-Seed-1.8 | volcengine/doubao-seed-1.8 | 256K | 64K | Input: $0.11 Output: $0.28 Cache Read: $0.02 Cache Write: $0.0024 | Model: 0.055 Completion: 2.545 Cache: 0.182 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, video Out: text | Released: 2025-12-18 |
| Doubao-Seed-2.0-pro | volcengine/doubao-seed-2.0-pro | 256K | 64K | Input: $0.45 Output: $2.24 Cache Read: $0.09 Cache Write: $0.0024 | Model: 0.225 Completion: 4.978 Cache: 0.200 | 📎 🧠 🔧 🌡️ | 2026-02-14 | In: text, image, video Out: text | Released: 2026-02-14 |
| Doubao-Seed-2.0-mini | volcengine/doubao-seed-2.0-mini | 256K | 64K | Input: $0.03 Output: $0.28 Cache Read: $0.01 Cache Write: $0.0024 | Model: 0.015 Completion: 9.333 Cache: 0.333 | 📎 🧠 🔧 🌡️ | 2026-02-14 | In: text, image, video Out: text | Released: 2026-02-14 |
| Doubao-Seed-Code | volcengine/doubao-seed-code | 256K | 64K | Input: $0.17 Output: $1.12 Cache Read: $0.03 | Model: 0.085 Completion: 6.588 Cache: 0.176 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2025-11-11 |
| Doubao-Seed-2.0-lite | volcengine/doubao-seed-2.0-lite | 256K | 64K | Input: $0.09 Output: $0.51 Cache Read: $0.02 Cache Write: $0.0024 | Model: 0.045 Completion: 5.667 Cache: 0.222 | 📎 🧠 🔧 🌡️ | 2026-02-14 | In: text, image, video Out: text | Released: 2026-02-14 |
| DeepSeek V3.2 | deepseek/deepseek-v3.2 | 128K | 64K | Input: $0.28 Output: $0.43 | Model: 0.140 Completion: 1.536 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-12-05 |
| DeepSeek-V3.2 (Non-thinking Mode) | deepseek/deepseek-chat | 128K | 64K | Input: $0.28 Output: $0.42 Cache Read: $0.03 | Model: 0.140 Completion: 1.500 Cache: 0.107 | 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-12-01 |
| DeepSeek-V3.2-Exp | deepseek/deepseek-v3.2-exp | 163K | 64K | Input: $0.22 Output: $0.33 | Model: 0.110 Completion: 1.500 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-09-29 |
| Kimi K2 0905 | moonshotai/kimi-k2-0905 | 262K | 64K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-09-04 |
| Kimi K2.5 | moonshotai/kimi-k2.5 | 262K | 64K | Input: $0.58 Output: $3.02 Cache Read: $0.1 | Model: 0.290 Completion: 5.207 Cache: 0.172 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, video Out: text | Released: 2026-01-27 |
| Kimi K2 Thinking | moonshotai/kimi-k2-thinking | 262K | 64K | Input: $0.6 Output: $2.5 Cache Read: $0.15 | Model: 0.300 Completion: 4.167 Cache: 0.250 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-11-06 |
| Kimi K2 Thinking Turbo | moonshotai/kimi-k2-thinking-turbo | 262K | 64K | Input: $1.15 Output: $8 Cache Read: $0.15 | Model: 0.575 Completion: 6.957 Cache: 0.130 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-11-06 |
| ERNIE 5.0 | baidu/ernie-5.0-thinking-preview | 128K | 64K | Input: $0.84 Output: $3.37 | Model: 0.420 Completion: 4.012 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, video Out: text | Released: 2026-01-22 |
| Gemini 2.5 Flash | google/gemini-2.5-flash | 1M | 64K | Input: $0.3 Output: $2.5 Cache Read: $0.07 Cache Write: $1 | Model: 0.150 Completion: 8.333 Cache: 0.233 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: pdf, image, text, audio Out: text | Released: 2025-06-17 |
| Gemini 3 Flash Preview | google/gemini-3-flash-preview | 1M | 64K | Input: $0.5 Output: $3 Cache Read: $0.05 Cache Write: $1 | Model: 0.250 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, pdf, audio Out: text | Released: 2025-12-17 |
| Gemini 2.5 Flash Lite | google/gemini-2.5-flash-lite | 1M | 64K | Input: $0.1 Output: $0.4 Cache Read: $0.03 Cache Write: $1 | Model: 0.050 Completion: 4.000 Cache: 0.300 | 📎 🔧 🌡️ | 2025-01-01 | In: pdf, image, text, audio Out: text | Released: 2025-07-22 |
| Gemini 3 Pro Preview | google/gemini-3-pro-preview | 1M | 64K | Input: $2 Output: $12 Cache Read: $0.2 Cache Write: $4.5 | Model: 1.000 Completion: 6.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, pdf, audio, video Out: text | Released: 2025-11-18 |
| Gemini 2.5 Pro | google/gemini-2.5-pro | 1M | 64K | Input: $1.25 Output: $10 Cache Read: $0.31 Cache Write: $4.5 | Model: 0.625 Completion: 8.000 Cache: 0.248 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: pdf, image, text, audio, video Out: text | Released: 2025-06-17 |
| GLM 5 | z-ai/glm-5 | 200K | 128K | Input: $0.58 Output: $2.6 Cache Read: $0.14 | Model: 0.290 Completion: 4.483 Cache: 0.241 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-02-12 |
| GLM 4.7 FlashX | z-ai/glm-4.7-flashx | 200K | 64K | Input: $0.07 Output: $0.42 Cache Read: $0.01 | Model: 0.035 Completion: 6.000 Cache: 0.143 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-01-19 |
| GLM 4.5 Air | z-ai/glm-4.5-air | 128K | 64K | Input: $0.11 Output: $0.56 Cache Read: $0.02 | Model: 0.055 Completion: 5.091 Cache: 0.182 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-07-25 |
| GLM 4.5 | z-ai/glm-4.5 | 128K | 64K | Input: $0.35 Output: $1.54 Cache Read: $0.07 | Model: 0.175 Completion: 4.400 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-07-25 |
| GLM 4.6V Flash (Free) | z-ai/glm-4.6v-flash-free | 200K | 64K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, video Out: text | Released: 2025-12-08 |
| GLM 4.6 | z-ai/glm-4.6 | 200K | 64K | Input: $0.35 Output: $1.54 Cache Read: $0.07 | Model: 0.175 Completion: 4.400 Cache: 0.200 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-09-30 |
| GLM 4.7 | z-ai/glm-4.7 | 200K | 64K | Input: $0.28 Output: $1.14 Cache Read: $0.06 | Model: 0.140 Completion: 4.071 Cache: 0.214 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-12-23 |
| GLM 4.7 Flash (Free) | z-ai/glm-4.7-flash-free | 200K | 64K | Input: $0 Output: $0 | - | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-01-19 |
| GLM 4.6V FlashX | z-ai/glm-4.6v-flash | 200K | 64K | Input: $0.02 Output: $0.21 Cache Read: $0.0043 | Model: 0.010 Completion: 10.500 Cache: 0.215 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, video Out: text | Released: 2025-12-08 |
| GLM 4.6V | z-ai/glm-4.6v | 200K | 64K | Input: $0.14 Output: $0.42 Cache Read: $0.03 | Model: 0.070 Completion: 3.000 Cache: 0.214 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, video Out: text | Released: 2025-12-08 |
| Qwen3-Max-Thinking | qwen/qwen3-max | 256K | 64K | Input: $1.2 Output: $6 | Model: 0.600 Completion: 5.000 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-01-23 |
| Qwen3-Coder-Plus | qwen/qwen3-coder-plus | 1M | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-07-23 |
| Grok Code Fast 1 | x-ai/grok-code-fast-1 | 256K | 64K | Input: $0.2 Output: $1.5 Cache Read: $0.02 | Model: 0.100 Completion: 7.500 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-08-26 |
| Grok 4 Fast | x-ai/grok-4-fast | 2M | 64K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2025-09-19 |
| Grok 4 | x-ai/grok-4 | 256K | 64K | Input: $3 Output: $15 Cache Read: $0.75 | Model: 1.500 Completion: 5.000 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text Out: text | Released: 2025-07-09 |
| Grok 4.1 Fast Non Reasoning | x-ai/grok-4.1-fast-non-reasoning | 2M | 64K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2025-11-20 |
| Grok 4.1 Fast | x-ai/grok-4.1-fast | 2M | 64K | Input: $0.2 Output: $0.5 Cache Read: $0.05 | Model: 0.100 Completion: 2.500 Cache: 0.250 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2025-11-20 |
| GPT-5 Codex | openai/gpt-5-codex | 400K | 64K | Input: $1.25 Output: $10 Cache Read: $0.12 | Model: 0.625 Completion: 8.000 Cache: 0.096 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2025-09-23 |
| GPT-5.2-Codex | openai/gpt-5.2-codex | 400K | 64K | Input: $1.75 Output: $14 Cache Read: $0.17 | Model: 0.875 Completion: 8.000 Cache: 0.097 | 📎 🧠 🔧 | 2025-01-01 | In: text, image, pdf Out: text | Released: 2026-01-15 |
| GPT-5.1 | openai/gpt-5.1 | 400K | 64K | Input: $1.25 Output: $10 Cache Read: $0.12 | Model: 0.625 Completion: 8.000 Cache: 0.096 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text, pdf Out: text | Released: 2025-11-13 |
| GPT-5.1 Chat | openai/gpt-5.1-chat | 128K | 64K | Input: $1.25 Output: $10 Cache Read: $0.12 | Model: 0.625 Completion: 8.000 Cache: 0.096 | 📎 🔧 🌡️ | 2025-01-01 | In: pdf, image, text Out: text | Released: 2025-11-13 |
| GPT-5.1-Codex-Mini | openai/gpt-5.1-codex-mini | 400K | 64K | Input: $0.25 Output: $2 Cache Read: $0.03 | Model: 0.125 Completion: 8.000 Cache: 0.120 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text Out: text | Released: 2025-11-13 |
| GPT-5.2 | openai/gpt-5.2 | 400K | 64K | Input: $1.75 Output: $14 Cache Read: $0.17 | Model: 0.875 Completion: 8.000 Cache: 0.097 | 📎 🧠 🔧 | 2025-01-01 | In: image, text, pdf Out: text | Released: 2025-12-11 |
| GPT-5 | openai/gpt-5 | 400K | 64K | Input: $1.25 Output: $10 Cache Read: $0.12 | Model: 0.625 Completion: 8.000 Cache: 0.096 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, pdf Out: text | Released: 2025-08-07 |
| GPT-5.1-Codex | openai/gpt-5.1-codex | 400K | 64K | Input: $1.25 Output: $10 Cache Read: $0.12 | Model: 0.625 Completion: 8.000 Cache: 0.096 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2025-11-13 |
| MiniMax: MiniMax M2.5 highspeed | minimax/minimax-m2.5-lightning | 204.8K | 131.1K | Input: $0.6 Output: $4.8 Cache Read: $0.06 Cache Write: $0.75 | Model: 0.300 Completion: 8.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-02-13 |
| MiniMax M2.1 | minimax/minimax-m2.1 | 204K | 64K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.38 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-12-22 |
| MiniMax M2 | minimax/minimax-m2 | 204K | 64K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.38 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2025-10-27 |
| MiniMax M2.5 | minimax/minimax-m2.5 | 204.8K | 131.1K | Input: $0.3 Output: $1.2 Cache Read: $0.03 Cache Write: $0.375 | Model: 0.150 Completion: 4.000 Cache: 0.100 | 🧠 🔧 🌡️ | 2025-01-01 | In: text Out: text | Released: 2026-02-13 |
| Claude 3.5 Sonnet (Retiring Soon) | anthropic/claude-3.5-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2025-01-01 | In: text, image, pdf Out: text | Released: 2024-10-22 |
| Claude 3.7 Sonnet | anthropic/claude-3.7-sonnet | 200K | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, pdf Out: text | Released: 2025-02-24 |
| Claude Opus 4.1 | anthropic/claude-opus-4.1 | 200K | 64K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text, pdf Out: text | Released: 2025-08-05 |
| Claude Sonnet 4.6 | anthropic/claude-sonnet-4.6 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2026-02-18 |
| Claude Haiku 4.5 | anthropic/claude-haiku-4.5 | 200K | 64K | Input: $1 Output: $5 Cache Read: $0.1 Cache Write: $1.25 | Model: 0.500 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2025-01-01 | In: image, text Out: text | Released: 2025-10-15 |
| Claude 3.5 Haiku | anthropic/claude-3.5-haiku | 200K | 64K | Input: $0.8 Output: $4 Cache Read: $0.08 Cache Write: $1 | Model: 0.400 Completion: 5.000 Cache: 0.100 | 📎 🔧 🌡️ | 2025-01-01 | In: text, image Out: text | Released: 2024-11-04 |
| Claude Opus 4.5 | anthropic/claude-opus-4.5 | 200K | 64K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: pdf, image, text Out: text | Released: 2025-11-24 |
| Claude Opus 4 | anthropic/claude-opus-4 | 200K | 64K | Input: $15 Output: $75 Cache Read: $1.5 Cache Write: $18.75 | Model: 7.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 4 | anthropic/claude-sonnet-4 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text, pdf Out: text | Released: 2025-05-22 |
| Claude Sonnet 4.5 | anthropic/claude-sonnet-4.5 | 1M | 64K | Input: $3 Output: $15 Cache Read: $0.3 Cache Write: $3.75 | Model: 1.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: text, image, pdf Out: text | Released: 2025-09-29 |
| Claude Opus 4.6 | anthropic/claude-opus-4.6 | 1M | 128K | Input: $5 Output: $25 Cache Read: $0.5 Cache Write: $6.25 | Model: 2.500 Completion: 5.000 Cache: 0.100 | 📎 🧠 🔧 🌡️ | 2025-01-01 | In: image, text Out: text | Released: 2026-02-06 |
Zhipu AI¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5 | glm-5 | 204.8K | 131.1K | Input: $1 Output: $3.2 Cache Read: $0.2 Cache Write: $0 | Model: 0.500 Completion: 3.200 Cache: 0.200 | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-11 |
| GLM-4.6V | glm-4.6v | 128K | 32.8K | Input: $0.3 Output: $0.9 | Model: 0.150 Completion: 3.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-12-08 |
| GLM-4.5V | glm-4.5v | 64K | 16.4K | Input: $0.6 Output: $1.8 | Model: 0.300 Completion: 3.000 | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-08-11 |
| GLM-4.7 | glm-4.7 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.11 Cache Write: $0 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-4.6 | glm-4.6 | 204.8K | 131.1K | Input: $0.6 Output: $2.2 Cache Read: $0.11 Cache Write: $0 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.7-Flash | glm-4.7-flash | 200K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2026-01-19 |
| GLM-4.5-Flash | glm-4.5-flash | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5 | glm-4.5 | 131.1K | 98.3K | Input: $0.6 Output: $2.2 Cache Read: $0.11 Cache Write: $0 | Model: 0.300 Completion: 3.667 Cache: 0.183 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5-Air | glm-4.5-air | 131.1K | 98.3K | Input: $0.2 Output: $1.1 Cache Read: $0.03 Cache Write: $0 | Model: 0.100 Completion: 5.500 Cache: 0.150 | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
Zhipu AI Coding Plan¶
📖 API Address | 📚 Official Documentation
| Model | Model ID | Context | Output | Pricing (1M) | NewAPI Ratios | Capabilities | Knowledge | Modalities | Details |
|---|---|---|---|---|---|---|---|---|---|
| GLM-5 | glm-5 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | - | In: text Out: text | Released: 2026-02-11 |
| GLM-4.6V-Flash | glm-4.6v-flash | 128K | 32.8K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-12-08 |
| GLM-4.6V | glm-4.6v | 128K | 32.8K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-12-08 |
| GLM-4.5V | glm-4.5v | 64K | 16.4K | Input: $0 Output: $0 | - | 📎 🧠 🔧 🌡️ | 2025-04 | In: text, image, video Out: text | Open Weights Released: 2025-08-11 |
| GLM-4.7 | glm-4.7 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-12-22 |
| GLM-4.6 | glm-4.6 | 204.8K | 131.1K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-09-30 |
| GLM-4.5-Flash | glm-4.5-flash | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5 | glm-4.5 | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |
| GLM-4.5-Air | glm-4.5-air | 131.1K | 98.3K | Input: $0 Output: $0 Cache Read: $0 Cache Write: $0 | - | 🧠 🔧 🌡️ | 2025-04 | In: text Out: text | Open Weights Released: 2025-07-28 |