Mistral Small 3.2 24B Instruct 2506

Mistral Small 3.2 24B Instruct 2506 is a text model from DeepInfra with a context window of 128K tokens and max output of 128K tokens. Pricing starts at 0.07 per million input tokens and 0.20 per million output tokens (cheapest at Mistral AI).

Price Comparison by Provider

Compare prices for Mistral Small 3.2 24B Instruct 2506 across different providers. The same model may be available through multiple providers at different price points.

• Chart
• Table

Provider	Model Key	Input Price, $	Output Price, $
OVHcloud	ovhcloud/Mistral-Small-3.2-24B-Instruct-2506	0.090	0.280
OpenRouter	openrouter/mistralai/mistral-small-3.2-24b-instruct	0.100	0.300
Mistral AI	mistral/mistral-small-3-2-2506	0.060	0.180
DeepInfra	deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506	0.075	0.200

All Variants

All available versions, regions, and API endpoints for Mistral Small 3.2 24B Instruct 2506.

Model Key	Provider	Mode	Input Price, $	Output Price, $	Context	Max Output	Vision	Functions
deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506	DeepInfra	Text	0.075	0.200	128K	128K	no	yes
mistral/mistral-small-3-2-2506	Mistral AI	Text	0.060	0.180	131K	131K	yes	yes
openrouter/mistralai/mistral-small-3.2-24b-instruct	OpenRouter	Text	0.100	0.300	32K	N/A	no	no
ovhcloud/Mistral-Small-3.2-24B-Instruct-2506	OVHcloud	Text	0.090	0.280	128K	128K	yes	yes