Mistral Small 3.1

24B Apache 2.0 multimodal model with up to 128K context and about 150 tokens per second, released in Base and Instruct versions.

Understands

text, images

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.