AI Models / Compare
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 genera
- Creator
- Mistral AI
- Lifecycle
- Active
- Context
- 256.0K
- Max output
- —
- Released
- Aug 1, 2025
- Status
- up
- Input
- $0.30 / 1M tokens
- Output
- $0.90 / 1M tokens
- Cached read
- $0.03 / 1M tokens
- Cached write
- — / 1M tokens
- Batch discount
- —%
- Source
- OpenRouter
- Verified
- Apr 5, 2026 (High)
Capabilities
- Modalities
- text→text
- Capabilities
- promptCachingfunctionCallingstructuredOutputs
Other models from Mistral AI
Codestral, Devstral 2, Devstral 2 2512, Devstral Medium, Devstral Small 1.1, Ministral 3 14B 2512, Ministral 3 3B 2512, Ministral 3 8B 2512, Mistral 7B Instruct v0.1, Mistral Large, Mistral Large 2407, Mistral Large 2411, Mistral Large 3, Mistral Large 3 2512, Mistral Medium 3, Mistral Medium 3.1, Mistral Nemo, Mistral Small 3, Mistral Small 3.1 24B, Mistral Small 3.2 24B, Mistral Small 4, Mistral Small 4, Mistral Small Creative, Mixtral 8x22B Instruct, Mixtral 8x7B Instruct, Pixtral Large 2411, Saba, Voxtral Small 24B 2507