Mistral Small 3.2 24B Instruct

Mistral Small 3.2 is a 24B open-weight model from Mistral AI that accepts text and image input, released in June 2025 as a minor update to Mistral Small 3.1. It improves instruction following, produces fewer repetitive or infinite generations, and has a more robust function-calling template.

Modalities

In / out price

$0.075 / $0.20per 1M

Context

128K

Max output

16K

Updated

Oct 22, 2026

Providers

2 routes

Compare providers by price, privacy, and speed.


Venice	Private	$0.0938	$0.25	—	256K	16K	—	—
DeepInfra	Private	$0.075	$0.20	—	128K	16K	—	—

Privacy

2 / 4

Private routing

Private tier

Anonymous
Private
TEE
E2EE

Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more

Features

Streaming

Tool calling

Vision

JSON/schema

Web search

Uptime

FAQ

Common questions about Mistral Small 3.2 24B Instruct.

Providers

Privacy

Features

Uptime

FAQ

Who created Mistral Small 3.2 24B Instruct?

When was Mistral Small 3.2 24B Instruct released?

How much does Mistral Small 3.2 24B Instruct cost?

What is the context window for Mistral Small 3.2 24B Instruct?

Is Mistral Small 3.2 24B Instruct multimodal?

Does Mistral Small 3.2 24B Instruct support tools and reasoning?

How private is Mistral Small 3.2 24B Instruct on AnonRouter?

Where can I use Mistral Small 3.2 24B Instruct?

Where can I read more about Mistral Small 3.2 24B Instruct?