Fast Mistral production model for chat, extraction, and cost-sensitive agents
Specification
most-agreed values
Context
256K
Max output
66K
Released
2026-03-16
Knowledge cutoff
2025-06
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.15
Output
$0.60
Cache read
$0.15
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| empiriolabs | $0.15 | $0.60 | $0.15 | — | 256K | 66K | — |
Other listings of this model
this page is one of them
The corpus files Mistral Small 4 under several keys. This page is the mistral-small-4 listing. The full record — every host, every price and every benchmark score — is on the main Mistral Small 4 page.
More from Mistral
most-hosted first