name = "Pixtral 12B"
description = "Mistral vision-language model for image understanding and multimodal chat"
family = "pixtral"
release_date = "2024-09-01"
last_updated = "2024-09-01"
attachment = true
reasoning = false
temperature = true
knowledge = "2024-09"
tool_call = true
open_weights = true

[cost]
input = 0.15
output = 0.15

[limit]
context = 128_000
output = 128_000

[modalities]
input = ["text", "image"]
output = ["text"]