Codestral 25.08
Mistral · Released 30 Jul 2025 · codestral-2508
$0.30
Input price / 1M tokens
#9 of 61, cheapest first
$0.90
Output price / 1M tokens
#6 of 61, cheapest first
128K
Context window
#70 of 71
–
Output tokens / second
Summary
Codestral 25.08 is a proprietary model from Mistral, released on 30 Jul 2025.
At $0.30 input and $0.90 output per million tokens, it is #9 of 61 on input price, cheapest first.
Its 128K-token context window ranks #70 of 71.
Mistral's code model for low-latency, high-frequency tasks such as fill-in-the-middle completion and code generation. It is still the current Codestral version.
Benchmarks · 0 reported
No benchmark score we could source for this model. We show scores only with a source link.
Sources
- API ID, version 25.08, date, Premier status, context, price, FIM endpoint: docs.mistral.ai/models/codestral-25-08, checked 2 Oct 2026
- cached input price: docs.mistral.ai/inference/pricing, checked 2 Oct 2026
- batch discount, free plan API credits: mistral.ai/pricing, checked 2 Oct 2026
- launch post (relative gains only): mistral.ai/news/codestral-25-08, checked 2 Oct 2026
Building on Codestral 25.08?
Get the architecture right before the bill arrives.
We size caching, routing and fallbacks for your workload on a free call, and tell you where a cheaper model is good enough.