MistralbalancedVisionTool use

Mistral Medium 3.5

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...

262K context·~197K words·
Context window262Ktokens

Context window

This model accepts 262K tokens in one request (~197K words of text).

Context window size262K tokens
4K32K128K1M10M

What fits in one request

  • Short document
    About 1,500 words of text
    Fits
  • Long document
    About 37K words of text
    Fits
  • Small codebase
    About 150K words of text
    Fits
  • Full novel
    About 375K words of text
    Won't fit

Specifications

Context size, pricing, and release info in one place.

Context window
262,144 tokens (262K)
Speed tier
balanced
Provider
Mistral
Release date
Apr 2026

Capabilities

See which features this model supports, such as vision, tools, and streaming.

Supported (5)
Vision
Supported
Tool use
Supported
Function calling
Supported
Extended thinking
Supported
Streaming
Supported
Not supported (3)
Web search
Not supported
Batch API
Not supported
Prompt caching
Not supported

Best for

Jump to a guide or ranking that matches each workload.

Compare Mistral Medium 3.5

Open a side-by-side comparison with one click.

Frequently asked questions

Short answers about context size and how this model behaves.

Mistral Medium 3.5 has a context window of 262K tokens (262,144 tokens). This large window is well-suited for long document analysis, extensive codebases, and multi-session agent workflows.

More from Mistral

Other models by Mistral in our catalog.

Powered by Mem0

Use a smaller model.
Get better results.

Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model