All Models
Codestral 2508
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)
Available Providers (10)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 NanoGPT | mistralai/codestral-2508 | $0.30/MTok | $0.90/MTok | 256K | 32.8K | |
 LLM Gateway | mistral/codestral-2508 | $0.30/MTok | $0.90/MTok | 256K | 256K | |
 Vercel AI Gateway | mistral/codestral | $0.30/MTok | $0.90/MTok | 256K | 4.1K | |
 DevPass (LLM Gateway) | codestral-2508 | $0.30/MTok | $0.90/MTok | 256K | 16.4K | |
 Kilo Gateway | mistralai/codestral-2508 | $0.30/MTok | $0.90/MTok | 256K | 204.8K | |
 Merge Gateway | mistral/codestral-latest | $0.30/MTok | $0.90/MTok | 256K | 4.1K | |
 OpenRouter | mistralai/codestral-2508 | $0.30/MTok | $0.90/MTok | 256K | 204.8K | |
 Mistral | codestral-latest | $0.30/MTok | $0.90/MTok | 256K | 4.1K | |
 Eden AI | mistral/codestral-latest | $0.30/MTok | $0.90/MTok | 256K | 4.1K | |
 Cortecs | codestral-2508 | $0.37/MTok | $1.10/MTok | 256K | 256K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output