Analysis Summary
Mistral's Codestral 2508 is a text-and-file model positioned for coding workflows. It lists a 256,000-token context window, tool use, and function calling, which make it suitable for evaluation on code and file-based tasks. No benchmark results are provided for this version, so its coding quality and reliability cannot be confirmed from the available data.
The long context and file input can support trials that involve larger code or document inputs. Listed pricing is $0.30 per million input tokens and $0.90 per million output tokens. The available information does not establish vision support, nor does it show how reliably the model handles complex multi-step engineering work.
Test it against representative code tasks with human review and regression checks. It is a reasonable candidate for a coding pilot, but benchmark evidence is needed before assigning it production engineering work.
Assessed September 23, 2026
Editorial notes
Codestral 2508 is a coding-oriented model with a 256K context window, file input, tool use, and function calling; benchmark results are not listed for this version.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
Codestral 2508 is a coding-oriented model with a 256K context window, file input, tool use, and function calling; benchmark results are not listed for this version.
How Mistral: Codestral 2508 compares
Its 256K-token context window is larger than 56% of the models we list. At $0.30 per million input tokens it is cheaper than 43% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.30 | $0.000300 |
| Output | $0.90 | $0.000900 |
What would Mistral: Codestral 2508 cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 753 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Mistral: Codestral 2508 for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout 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
Explore Related Models
Frequently asked questions about Mistral: Codestral 2508
How much does Mistral: Codestral 2508 cost?
Mistral: Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens.
What is the context window of Mistral: Codestral 2508?
Mistral: Codestral 2508 has a context window of 256,000 tokens (256K).
What can Mistral: Codestral 2508 do?
Mistral: Codestral 2508 supports tool use and function calling.
Who created Mistral: Codestral 2508?
Mistral: Codestral 2508 is developed by Mistral and was released on August 1, 2025.
Benchmarks from Artificial Analysis, pricing from the OpenRouter API, and verdicts from our own testing.
Last updated: November 17, 2026 7:38 pm