name = "Llama 3.2 11B Vision Instruct"
description = "Open Llama multimodal model for image understanding and text reasoning"
family = "llama"
release_date = "2024-09-25"
last_updated = "2024-09-25"
attachment = true
reasoning = false
temperature = true
tool_call = false
structured_output = false
open_weights = true

[cost]
input = 0.0485
output = 0.676

[limit]
context = 128_000
output = 128_000

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