Model registry / Mistral AI / Mistral Small / Mistral Small 3.2
Mistral Small 3.2
Efficient Mistral model for fast chat, extraction, and production assistants
Line
Mistral Small
Weights
Open
Released
2025-06-20
Context
128K
Input
$0.10 / 1M
Output
$0.30 / 1M
Max output
16K
Coverage
not covered yet
Overview
Mistral Small 3.2 is an efficient Mistral model for fast chat, extraction, and production assistants. It is the first version of the mistral-small line in the registry. It has a context window of 128,000 tokens and a maximum output of 16,384 tokens. Pricing starts at $0.10 per million input tokens and $0.30 per million output tokens. The weights are open. It accepts image and text inputs and returns text. It supports tool calling but not reasoning mode.
Specs
Pricing
First version of its line in the registry.
Strengths
- 128k context window
- 16k max output tokens
- Tool calling supported
- Accepts image and text inputs
- Open weights
Best for
- Reach for it for fast chat assistants
- Reach for it for extraction from text and images
- Reach for it for production assistant workflows
- Reach for it for tool-calling applications
How to access
3 hosts serve this model at the price above · the maker's documentation
Mistral Small: 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 and output limit?
- The context window is 128,000 tokens and the maximum output is 16,384 tokens.
- Does it support reasoning mode?
- No, reasoning mode is not supported. It does support tool calling.
- What is the price per token?
- Pricing starts at $0.10 per million input tokens and $0.30 per million output tokens.