Model Terminal
Codestral 2508
Codestral 2508 is Mistral AI's flagship code-specialized large language model, designed for developer workflows including code completion, fill-in-the-middle, code correction, and test generation. It features a 256K-token context window and is available via the Mistral API, OpenRouter, and enterprise deployment options (cloud, VPC, on-prem). Source: supabase.
Value score
Not scored
Context
—
tokens
Max output
—
tokens
Price
—
Capability radar
Peer value bars
Identity
- Developer
- Mistral AI
- Openness
- —
- Modalities
- —
- Release
- —
- Knowledge cutoff
- —
- Deprecation
- —
- API docs
- —
Benchmarks
No benchmark scores yet.
Compare nearby
Pricing
- Input / 1M
- —
- Output / 1M
- —
- Speed
- —
