Model

Llama-3.2-11B-Vision-Instruct

Name: Llama-3.2-11B-Vision-Instruct
Brand: meta

Open multimodal Llama model for image understanding, captioning, and visual QA

2 providersreleased Sep 25, 2024knowledge cutoff 2023-12open weights

$0.055

best input /M · Inference

$0.055

best output /M

128K

context window

max output

Compare providers (sorted by listed input price)

Provider	Input /M	Output /M	Cache read /M	Cache write /M	Context	Capabilities	Status	Updated
Nvidia meta/llama-3.2-11b-vision-instruct	—	—	—	—	128K	no reasoningtoolsstructuredvision		Sep 18, 2024
Inference meta/llama-3.2-11b-vision-instruct	$0.055	$0.055	—	—	16K	no reasoningtoolsno structuredvision		Jan 1, 2025

Price badge

![Llama-3.2-11B-Vision-Instruct price](https://models.sutraworks.ai/badge/meta/llama-3.2-11b-vision-instruct.svg)

https://models.sutraworks.ai/badge/meta/llama-3.2-11b-vision-instruct.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Weights

Hugging Face

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.