Codestral 25.08
Mistral code model for low-latency completion, fill-in-the-middle, and code generation
Live
Open / InstallLast updated October 23, 2026
Description
Mistral code model for low-latency completion, fill-in-the-middle, and code generation. Supports a context window of 256,000 tokens. Supports tool calling. Input priced at $0.3 per million tokens. Weights are not publicly released; access is via the provider API.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
Mistral
Platform
api
Pricing model
paid
Categories
- Coding
- Productivity
Tags
- llm
- closed-weights
- mistral
- codestral
- tool-calling
- text
- pdf
Capabilities
- Text generation
- 256,000 token context
- Tool calling
- File attachments
Information
TypeLarge Language Model
Model TypeText Generation
SourceModels Dev
AddedOctober 7, 2026