Mistral Nemo
Mistral AI · Jul 19, 2024
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese,…
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)
mistralai/codestral-2508Codestral 2508 is an API model from Mistral AI, released on Aug 1, 2025, with a context window of 256,000 tokens, pricing of $0.3 per million input tokens and $0.9 per million output tokens. It accepts file, text input and produces text output.
At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.0039.
Specs are sourced from OpenRouter and were last checked on Nov 20, 2026. Always confirm current pricing and limits with the provider before production use.
Codestral 2508 supports a context window of 256,000 tokens.
Codestral 2508 is listed at $0.3 per million input tokens and $0.9 per million output tokens on OpenRouter.
Codestral 2508 was published on Aug 1, 2025.
Codestral 2508 accepts file, text input and produces text output.