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)

Pricing and specs

Providermistralai
Input price$0.300 / 1M tokens
Output price$0.900 / 1M tokens
Context window256k tokens
Max outputNot specified
Modalitiestext, file
Model IDmistralai/codestral-2508

What a typical call costs

A 1,000-token prompt with a 500-token answer on Mistral: Codestral 2508 costs roughly $0.00075. Use the OpenRouter cost calculator to price your own prompt across 400+ models, or the token counter to measure prompt length first.

Run your prompts on Mistral: Codestral 2508

PromNest stores your prompt library and lets you run any prompt on Mistral: Codestral 2508 with your own OpenRouter key — including side-by-side comparison with other models. Browse 1,000+ ready-made prompt templates to start.

Alternatives from mistralai

Mistral LargeMistral Large 2407Mistral: Ministral 3 14B 2512Mistral: Ministral 3 3B 2512Mistral: Ministral 3 8B 2512Mistral: Ministral 8BMistral: Mistral Large 3 2512Mistral: Mistral Medium 3

← Back to the full AI model catalog