Mistral: Codestral 2508mistralai
Mistral: Codestral 2508: $0.30/1M input, $0.90/1M output, 256K context. 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)
API Pricing (per 1M tokens)
| Input | $0.30 |
| Output | $0.90 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.45 |
Specs & Performance
| Context Length | 256K |
| Max Output | 205K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text, file → text |
More from mistralai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Mistral: Codestral 2508 API cost?
Mistral: Codestral 2508 costs $0.30/1M input tokens and $0.90/1M output tokens. Blended cost at a 3:1 ratio is about $0.45/1M tokens.
What is the context window of Mistral: Codestral 2508?
Mistral: Codestral 2508 supports a 256K token context window with up to 205K output tokens.
Is Mistral: Codestral 2508 worth it?
Mistral: Codestral 2508 has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.