Codestral 25.01

Code completion and generation model for 80+ languages with a 256K context, fill-in-the-middle, code correction and test generation; about 2x faster than the original Codestral, 86.6% on HumanEval Python.

Understands

text

This model cannot see images or video — you can only give it text. That matters if you planned to show it screenshots or documents with pictures.

Produces

text, code

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.