Free Mistral model via API
Updated:
Medium 3.5, Codestral, Devstral, and Mixtral available free directly or through OpenRouter, Together, and Groq.
Read more
A direct Mistral key and a router key are not interchangeable. Check coding models separately from instruct.
26 models found
| № | Model | Power | Provider | Parameters | Context | Limit | |
|---|---|---|---|---|---|---|---|
| 1 |
Mistral Small
|
⚖️ | Mistral AI | ? | 33K | 1 req/min · 500 tok/min | Open |
| 2 |
Mistral Nemo
|
⚖️ | Mistral AI | ? | 131K | 1 req/min · 500 tok/min | Open |
| 3 |
Codestral Mamba
|
⚡ | Mistral AI | ? | 256K | 1 req/min · 500 tok/min | Open |
| 4 |
Mistral Embed
|
⚖️ | Mistral AI | ? | 8K | 1 req/min · 500 tok/min | Open |
| 5 |
nim/mistralai/mixtral-8x22b-instruct-v01
|
⚖️ | Together AI | ? | 16K | Fair Use (По мере нагрузки серверов) | Open |
| 6 |
nim/nv-mistralai/mistral-nemo-12b-instruct
|
⚖️ | Together AI | 12B | 16K | Fair Use (По мере нагрузки серверов) | Open |
| 7 |
nim/mistralai/mixtral-8x7b-instruct-v01
|
⚖️ | Together AI | ? | 16K | Fair Use (По мере нагрузки серверов) | Open |
| 8 |
Mistral 7B v0.1
|
⚡ | Together AI | 7B | 33K | Fair Use (По мере нагрузки серверов) | Open |
| 9 |
Devstral Small 2505
|
⚖️ | Together AI | ? | 131K | Fair Use (По мере нагрузки серверов) | Open |
| 10 |
Mixtral 8X22b Instruct V0.1
|
⚖️ | Together AI | ? | 66K | Fair Use (По мере нагрузки серверов) | Open |
| 11 |
Magistral Small 2506
|
⚖️ | Together AI | ? | 41K | Fair Use (По мере нагрузки серверов) | Open |
| 12 |
Mixtral 8x7B Instruct V0.1 FP8 Lora
|
⚖️ | Together AI | ? | 33K | Fair Use (По мере нагрузки серверов) | Open |
| 13 |
Mistral 7B v0.3
|
⚡ | Cloudflare | 7B | 33K | 10,000 req/day | Open |
| 14 |
Mistral 7B v0.3
|
⚡ | HuggingFace | 7B | 33K | Fair Use (По мере нагрузки серверов) | Open |
| 15 |
Codestral 22b Instruct V0.1
|
⚖️ | NVIDIA Build | 22B | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 16 |
Mistral 7b Instruct V0.3
|
⚡ | NVIDIA Build | 7B | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 17 |
Mistral Large
|
🚀 | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 18 |
Mistral Large 2 Instruct
|
🚀 | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 19 |
Mistral Nemo 12b Instruct
|
⚖️ | NVIDIA Build | 12B | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 20 |
Mistral Nemo Minitron 8b 8k Instruct
|
⚡ | NVIDIA Build | 8B | 8K | Free serverless inference for development; limits and model availability may change. | Open |
| 21 |
Mistral Nemotron
|
⚖️ | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 22 |
Mixtral 8x22b V0.1
|
⚖️ | NVIDIA Build | ? | ? | Free serverless inference for development; limits and model availability may change. | Open |
| 23 |
Codestral Latest
|
⚡ | UnoRouter | ? | 256K | No-card free models use shared capacity and per-model limits; availability can change. | Open |
| 24 |
Mistral 7b Instruct
|
⚡ | UnoRouter | 7B | 25K | No-card free models use shared capacity and per-model limits; availability can change. | Open |
| 25 |
Mistral Nemotron
|
⚖️ | UnoRouter | ? | 128K | No-card free models use shared capacity and per-model limits; availability can change. | Open |
| 26 |
Mistral Small
|
⚖️ | UnoRouter | ? | 128K | No-card free models use shared capacity and per-model limits; availability can change. | Open |