Codestral
Mistral's specialized code model with broad language coverage and a 256k context window for large codebases.
Pricing
Input$0.30 / 1M checked Jul 19, 2026
Output$0.90 / 1M checked Jul 19, 2026
Free for non-commercial use via Mistral.
Cost bandBudget
Free tierFree API access for non-commercial use on Mistral La Plateforme.
Limits
Context window256k checked Jul 19, 2026
Max output32,768
Knowledge cutoffQ1 2024
DeploymentMistral La Plateforme, Azure AI
OpenAI-compatible APIYes
ModalitiesText
Where it fits
Best forCode completion, FIM (fill-in-the-middle), test generation, and editor integrations.
Business fitBest-in-class Mistral model for pure code tasks; often plugged into VS Code / Cursor via Continue.
Capabilities
FIM (fill-in-the-middle)Function callingBatch inference
Benchmark scores
Composite76 / 100
Coding88 / 100 (HumanEval)
Reasoning64 / 100 (MMLU-Pro)
Long context72 / 100
Instruction following74 / 100 (MT-Bench)
Editorial aggregate of published benchmark results as of Jan 1, 2025. These are not independent measurements run by this site.
Change history
No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.
Data
Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/mistralai/codestral-2508
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.