pixtral-12b-2409
Mistral · 1 configuration
Intelligence—
Input / 1M$0.22
Output / 1M$0.22
Context128K
Tariff: Cortecs · Source: models-dev · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
◌
No pair of measurements available
Change the filters or pick another benchmark. Missing values are not estimated.
Selected: thinking default · Click a point to switch configuration
Pixtral 2409 12B is a state-of-the-art multimodal model with 12B parameters and a 400M vision encoder, natively trained on interleaved text and image data. It excels in tasks spanning vision-language reasoning, instruction following, and pure text understanding, making it highly effective for real-world multimodal applications.
This model is in the catalog but has no imported benchmarks. Capabilities are not estimated.
Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output4.1K
Catalog listing date2024-11-09