Mistral: Codestral 2508
Mistral's Codestral 2508 is a coding-focused model with a large 256K context window and tool use support, but the absence of benchmark data means it cannot be rated highly — businesses should await verified performance results before committing.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Mistral |
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.30 | $0.000300 |
| Output | $0.90 | $0.000900 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
