AI model · Mistral
Codestral 2508
Model ID: mistralai/codestral-2508
- Input
- $0.30 per 1M tokens
- Output
- $0.90 per 1M tokens
- Context
- 256K tokens at once
- Max output
- 205K tokens per reply
- Released
- 1 Aug 2025 Mistral
What it can do
- NoReasoning
- YesTool calling
- NoImage input
- NoOpen weights
- NoFree to use
Takes text, file; gives text.
How its listing describes it
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.
Sources
- Mistral: Codestral 2508 on OpenRouter — read 2 Oct 2026