Mistral logo

Codestral 2508: Pricing, Context Window & Benchmarks

by Mistral

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)

Chat with Codestral 2508
Input Price
$0.30/1M tokens
Output Price
$0.90/1M tokens
Context Window
256,000 tokens
Modalities
text

What you can do with Codestral 2508

Everyday Q&A and clear explanations

Writing help (emails, posts, summaries)

Idea generation and brainstorming

Learning support with step-by-step guidance

Benchmarks not available

This model isn't listed on Artificial Analysis yet. Showing OpenRouter specs below.

Metric Value
Provider Mistral
Context Window 256,000 tokens
Input Price $0.30/1M tokens
Output Price $0.90/1M tokens
Release Date Aug 1, 2025
Modalities text
Capabilities N/A

Compare Codestral 2508 to other models

See how it stacks up on price, quality, and overall performance.

Frequently asked questions

What is Codestral 2508 good for?

Use Codestral 2508 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Codestral 2508 cost?

Pricing is based on usage. Current rates are $0.30/1M tokens for input and $0.90/1M tokens for output.

Can I try Codestral 2508 for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Codestral 2508 support images or audio?

Codestral 2508 focuses on text-based tasks.

Pricing, context, and capability data are sourced from OpenRouter.