Mistral Medium 3.5 is a dense 128B instruction following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. It is particularly strong at reliable multi tool calling and long horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self hostable on as few as four GPUs and available under open weights.
Specification
most-agreed values
Context
262K
Max output
262K
Released
2026-04-30
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.65
Output
$8.25
Cache read
$1.65
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| requesty | $1.65 | $8.25 | $1.65 | — | 262K | 262K | — |
More from Mistral
most-hosted first