Pixtral 12B

mistral

A compact 12B multimodal model with image understanding alongside text capabilities.

Try Now

Capabilities

Tool Use

Image Input

Example Use Cases

Image understanding tasks

Multimodal with small footprint

Budget vision model

Technical Specifications

Context Window

128,000 tokens

Max Output

4,000 tokens

Cache Miss Cost

$0.15 per 1M tokens

Non-Reasoning Cost

$0.15 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Poor tool calling capabilities

Recommended Replacement

Mistral Medium 3.1