whichllmmodel
Back to Dashboard
💬 Text ModelOpen Source

Codestral 22B

by Mistral AI

✍️ Analysis by:the whichllmmodel Editorial Team|📅 Updated: June 2026
API Reference

Benchmark Evaluations

Codingswe-bench-pro

N/A

Reasoninggpqa-diamond

N/A

Pricing Details

Input Cost

$0.30

per 1M tokens
Output Cost

$0.90

per 1M tokens
Blended Cost

$0.45

based on 3:1 ratio
Context Window

32.77k tokens

Want to test this model?

Compare Codestral 22B dynamically against other top AI models on our comparison dashboard to optimize your choice.

Go to Dashboard

Quick Info

  • ProviderMistral AI
  • CategoryText / Chat Generation
  • LicenseOpen Source
  • AvailabilityAPI & Local
  • Hugging FaceView Repository ↗

Frequently Asked Questions

Codestral 22B has a blended cost of $0.45 per 1 million tokens (calculated using a standard 3:1 input-to-output token ratio). Its specific pricing is $0.30 per 1M input tokens and $0.90 per 1M output tokens.

Codestral 22B supports a context window of 32.77k tokens. This allows it to process large documents, codebase segments, or long chat histories in a single query session.

Codestral 22B scores N/A on coding evaluations (SWE-bench-pro) and N/A on reasoning tasks (GPQA-diamond).

Codestral 22B is an open source model developed by Mistral AI.