Codestral
View website
Mistral AI's 22B code generation model, released January 2025. Trained on 80+ languages; debuted #1 on LMSys Copilot Arena.
At a glance
- Context window
- 256K tokens
- Max output
- 33K tokens
- Knowledge cutoff
- Dec 2024
- Modalities
- Text Text → Text Text
Capabilities
Function calling
Function calling
Connect to external tools, APIs, and systems.
Code execution
Code execution
Write and execute code in a sandboxed environment.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
|
Mistral
|
$0.30 | $0.90 |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Compare with other models
Estimated prices shown. Actual costs may vary based on context length, batch size, caching, and provider-specific pricing tiers.