Mistral: Codestral 2508
Mistral AI · Text
Mistral code model for low-latency completion, fill-in-the-middle, and code generation
Model ID mistralai/codestral-2508Updated Jul 30, 2025
Pricing & billing
Billing unit: 1M tokens. Vendor reference price; conversion is approximate.
ItemUSD referenceList price (USD)
Input$0.30$0.30
Output$0.90$0.90
Cache read$0.03$0.03
Cache write—No public pricing—No public pricing
Specifications
- Form
- Text model
- Input modalities
- Text、File
- Output modalities
- Text
- Context length
- 256K
- Max output
- 205K
- Weights
- Closed
- Family
- codestral
- Released
- Jul 30, 2025
Uses and capabilities
Capabilities Text model、Function calling、Structured output、Prompt caching
Function calling
Structured output
Reasoning
Prompt caching
Open weights
Sources
Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.