← model directory
mistralai
Mistral: Codestral 2508
mistralai/codestral-2508
↓ runs free on your own hardwareMistral'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)
specs & pricing
- Type
- text
- Provider
- mistralai
- Model ID
- mistralai/codestral-2508
- Capabilities
- tools
- Context window
- 256K tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $0.33 / 1M tokens
- Output price
- $0.99 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.