Mistral logo

Mistral

Codestral 2508

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Input / 1M tokens
$0.300
Output / 1M tokens
$0.900
Context window
256K tokens
Provider
Mistral
Cached input / 1M
$0.030
Knowledge cutoff
2025-03-31

Performance

Median streaming throughput and first-token latency measured by Artificial Analysis.

Output tokens / sec
Time to first token