Mistral — free API
Updated:
Mistral general-purpose and coding models available directly or through compatible routers, including Medium 3.5, Codestral, and Devstral variants.
Read more
The list is built from current provider API responses. The same model may appear more than once because each endpoint has its own limits, context window, and free-tier rules. Individual model pages use stable URLs and update automatically.
25 models found
| № | Model | Power | Provider | Parameters | Context | Limit | |
|---|---|---|---|---|---|---|---|
| 1 |
|
⚖️ | Mistral AI | ? | 33K | 1 req/min · 500 tok/min | Open |
| 2 |
|
⚖️ | Mistral AI | ? | 131K | 1 req/min · 500 tok/min | Open |
| 3 |
|
⚡ | Mistral AI | ? | 256K | 1 req/min · 500 tok/min | Open |
| 4 |
|
⚖️ | Mistral AI | ? | 8K | 1 req/min · 500 tok/min | Open |
| 5 |
|
⚖️ | Together AI | ? | 16K | Fair Use (По мере нагрузки серверов) | Open |
| 6 |
|
⚖️ | Together AI | 12B | 16K | Fair Use (По мере нагрузки серверов) | Open |
| 7 |
|
⚖️ | Together AI | ? | 16K | Fair Use (По мере нагрузки серверов) | Open |
| 8 |
|
⚡ | Together AI | 7B | 33K | Fair Use (По мере нагрузки серверов) | Open |
| 9 |
|
⚖️ | Together AI | ? | 131K | Fair Use (По мере нагрузки серверов) | Open |
| 10 |
|
⚖️ | Together AI | ? | 66K | Fair Use (По мере нагрузки серверов) | Open |
| 11 |
|
⚖️ | Together AI | ? | 41K | Fair Use (По мере нагрузки серверов) | Open |
| 12 |
|
⚖️ | Together AI | ? | 33K | Fair Use (По мере нагрузки серверов) | Open |
| 13 |
|
⚡ | Cloudflare | 7B | 33K | 10,000 req/day | Open |
| 14 |
|
⚡ | HuggingFace | 7B | 33K | Fair Use (По мере нагрузки серверов) | Open |
| 15 |
|
⚖️ | NVIDIA Build | 22B | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 16 |
|
⚡ | NVIDIA Build | 7B | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 17 |
|
🚀 | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 18 |
|
🚀 | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 19 |
|
⚖️ | NVIDIA Build | 12B | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 20 |
|
⚡ | NVIDIA Build | 8B | 8K | Free serverless inference for development; limits and model availability may change. | Open |
| 21 |
|
⚖️ | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 22 |
|
⚖️ | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 23 |
|
⚡ | UnoRouter | ? | 256K | No-card free models use shared capacity and per-model limits; availability can change. | Open |
| 24 |
|
🚀 | UnoRouter | 675B | 256K | No-card free models use shared capacity and per-model limits; availability can change. | Open |
| 25 |
|
⚖️ | UnoRouter | ? | 128K | No-card free models use shared capacity and per-model limits; availability can change. | Open |