by Mistral AI

Mistral Small 4.

multimodal open weights datacenter 121B params 262K ctx
Cheapest input
$0.15/M
on Mistral La Plateforme
Cheapest output
$0.6/M
on Mistral La Plateforme
Smallest GPU
2× Nvidia Q RTX 8000
$0.54/hr
Description

About Mistral Small 4.

Mistral Small 4 is an Apache 2.0 open-weights model that merges Mistral's Instruct, Reasoning and Devstral lines into one. It is a mixture-of-experts design with 119 billion parameters, 6.5 billion active per token, using 4 of 128 experts. It takes text and images, returns text, and has a 256k context. Reasoning is switched on or off per request. Mistral aims it at chat assistants, coding agents, document extraction and research. The maker also publishes an NVFP4 checkpoint and a speculative decoding head, and suggests its own API if local serving falls short.

Context window

How much it can remember.

262K tokens ≈ 196,608 English words
4K 32K 128K 1M
Capabilities

What it can do.

· Vision input
· Audio input
· Video input
· Function calling
· Tool use
· JSON mode
✓ Streaming
· Fine-tuning