by Mistral AI· Released September 2024
Pixtral 12B is Mistral AI's first multimodal model, capable of processing both text and images. It is a 12-billion parameter model that excels at tasks like document understanding, image captioning, and visual question answering. Pixtral 12B is designed to be efficient and accessible, offering strong performance in a compact size.
Input cost
Free (open source)
Output cost
Free (open source)
Context window
128K tokens
Max output
—
Modalities
Parameters
12B
License
Apache-2.0
Multimodal tasks requiring understanding of both text and images, such as document analysis and visual question answering.
