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)
Specifications
| Provider | Mistral |
|---|---|
| Context window | 256,000 tokens (256K) |
| Input price | $0.3 / 1M tokens |
| Output price | $0.9 / 1M tokens |
| Input modalities | text, file |
| Output modalities | text |
| Model ID | mistralai/codestral-2508 |
Pricing is per 1M tokens, indicative pricing via OpenRouter (updated 2026-08-22); a provider's own list price may differ.
Frequently asked questions
How much does Codestral 2508 cost?
Indicative pricing (via OpenRouter, updated 2026-08-22) is $0.3 per 1M input tokens and $0.9 per 1M output tokens. A provider's own list price may differ. On Vincony, Codestral 2508 is available on credit-based pricing alongside 800+ other models.
What is Codestral 2508's context window?
Codestral 2508 supports a context window of up to 256,000 tokens (256K), which is how much text it can consider at once.
Who makes Codestral 2508?
Codestral 2508 is built by Mistral. You can access it — and compare it against other providers' models — through Vincony's multi-model platform.
How do I use Codestral 2508?
You can use Codestral 2508 directly through Mistral, or via Vincony, which aggregates 800+ models (including Codestral 2508) into one interface with side-by-side comparison and credit-based pricing.