Mistral AI

Codestral 2508

Generally available256K context

Summary

Codestral 2508 is a language model from Mistral AI, released on 1 Aug 2025. It accepts text and files and generates text, with a 256K-token context window and up to 205K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.30 per million input tokens and $0.90 per million output tokens (OpenRouter), across 1 provider we track.

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)

Last verified 4 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperMistral AI
Release date1 Aug 2025 [OpenRouter]
StatusGenerally available
Context window256K (256,000 tokens) [OpenRouter]
Max output205K tokens [OpenRouter]
Knowledge cutoff31 Mar 2025 [OpenRouter]
InputText and files [OpenRouter]
OutputText [OpenRouter]
Reasoning modeNo [OpenRouter]
Tool callingYes [OpenRouter]
Structured outputYes [OpenRouter]

Codestral 2508 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
mistralai/codestral-2508
$0.30$0.90$0.03256KOpenRouter, 4 Oct 2026

Frequently asked questions

What is the context window of Codestral 2508?

Codestral 2508 has a context window of 256,000 tokens (256K) and can generate up to 204,800 tokens in a single response, according to OpenRouter.

How much does the Codestral 2508 API cost?

Codestral 2508 is listed from $0.30 per million input tokens and $0.90 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

When was Codestral 2508 released?

Mistral AI released Codestral 2508 on 1 Aug 2025, according to OpenRouter.

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources