Model registry / Mistral AI / Mistral Medium / Mistral Medium 3.1
Mistral Medium 3.1
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Line
Mistral Medium
Weights
API only
Released
2025-08-12
Context
262K
Input
$0.40 / 1M
Output
$2.00 / 1M
Max output
262K
Coverage
not covered yet
Overview
Mistral Medium 3.1 is a Mistral AI model for multilingual chat, reasoning, and tool-assisted workflows. It is the first version of the mistral-medium line in the registry. It has a context window of 262144 tokens and a max output of 262144 tokens. Pricing starts at $0.40 per million input tokens and $2.00 per million output tokens. Weights are not open. It accepts image and text inputs, returns text, and supports tool calling. It does not have a reasoning mode.
Specs
Pricing
First version of its line in the registry.
Strengths
- Multilingual chat and reasoning
- Tool-assisted workflows
- 262k token context window
- 262k token max output
- Accepts image and text inputs
Best for
- Reach for it for multilingual chat and reasoning tasks
- Reach for it for tool-assisted workflows
- Reach for it for processing long documents with 262k context
- Reach for it for tasks needing image and text input
How to access
1 host serve this model at the price above · the maker's documentation
Mistral Medium: every version
The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.
FAQ
- What is the context window size?
- The context window is 262144 tokens, and the max output is also 262144 tokens.
- Does it support tool calling?
- Yes, it supports tool calling.
- Are the weights open?
- No, the weights are not open.