Model
Mistral Small 4.
Power
££
API cost
by Mistral AI
In plain English
A smaller Mistral model for everyday work. It can handle text and images, and you can download and adapt it yourself.
Good for
Chat assistants, document understanding, coding, and repeated tasks where cost and speed matter.
Things to be aware of
“Small” is relative. Running it yourself still needs substantial computing infrastructure. Test it on the work you need done before deciding that the lower price is a saving: checking and redoing weak results takes time too.
What Mistral AI says
“a hybrid model optimized for general chat, coding, agentic tasks, and complex reasoning”
Seen here: Mistral’s Small 4 announcement
What everyone else says
Artificial Analysis found Small 4 quick and relatively inexpensive on its tests, but below average for capability among the comparable models it assessed. Artificial Analysis: Mistral Small 4
- Context window
- 256.0K tokens
- Run it yourself
- Yes, under Apache 2.0
- API price
- $0.15 in / $0.60 out
- per million tokens