Flagship Mistral model for advanced reasoning, coding, and multilingual work
Mistral Large 2.1 is offered by 2 providers on this page. Its official list price is $2.00 per 1M input tokens and $6.00 per 1M output tokens.
The context window is 131,072 tokens, with an output limit of 16,384 tokens. It supports tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2024-11.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Merge Gateway | Gateway | $2.00 | $6.00 | — | — | 131,072 | 16,384 | |
| MistralOfficial | First-party | $2.00 | $6.00 | — | — | 131,072 | 16,384 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 13.8 | index | Source ↗ |
| SciCode | — | 29.2 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 6.1 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.