Mistral code model for completions, refactors, and developer IDE workflows
Codestral (latest) by mistral is offered by 4 providers on this page. Its official list price is $0.30 per 1M input tokens and $0.90 per 1M output tokens.
The context window is 256,000 tokens, with an output limit of 4,096 tokens. It supports tool use and structured output. 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 2024-10.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Vercel AI Gateway mistral/codestral | Cloud | $0.30 | $0.90 | $0.03 | — | 256,000 | 4,096 | |
| Merge Gateway | Gateway | $0.30 | $0.90 | — | — | 256,000 | 4,096 | |
| Eden AI | Gateway | $0.30 | $0.90 | $0.03 | — | 256,000 | 4,096 | |
| MistralOfficial | First-party | $0.30 | $0.90 | $0.03 | — | 256,000 | 4,096 |
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 |
|---|---|---|---|---|
| Aider Polyglot | — | 11.1 | percent correct | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.