TPSTokens Per Second

Mistral Small 4

Mistral AI🇫🇷 France
active

Next major release in the Mistral Small family, unifying capabilities of several flagship Mistral models. Combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities into a single system.

Compare with other models →
Context window256K tokens

Version History

4.0major

Major release unifying reasoning, multimodal, and coding capabilities. First Mistral model with configurable reasoning effort parameter and native multimodal support in the Small family.

mistral-small-4-2026-03-16major

Mistral Small 4 launches unifying Magistral reasoning, Pixtral multimodal, and agentic coding into one model. 262K context at $0.15/$0.60 per 1M tokens.

Benchmark Scores

Full leaderboard →
0.7%
LiveCodeBench

Coverage

model releaseMistral AI

Mistral AI Releases Small 4: 119B Parameter Open-Source Model with 256K Context Under Apache 2.0

Mistral AI has released Mistral Small 4, a 119B total parameter mixture-of-experts model with 256K context window and native multimodal capabilities. The model uses 128 experts with 4 active per token (6B active parameters) and is released under the Apache 2.0 license, marking Mistral's first unified model combining reasoning, multimodal, and coding capabilities.

2 min read
mistral-aiopen-sourcemixture-of-experts