Pass IndexThe State of AISign in

Llama Guard 3 11B Vision

Llama Guard 3 11B Vision is Meta's multimodal safety classifier: it evaluates the prompt text and the image together to decide whether a prompt is safe, using the vision understanding of Llama 3.2 11B-Vision.

text + image → text · made by Meta

$0.35$0.35per Mtok in / out
IBM watsonx · 2 sellers

Sold by 2 ways

SellerLaneRate
IBM watsonx cloudstandard$0.35per Mtok in$0.35per Mtok outraw.githubusercontent.com · read 2026-09-16
IBM watsonx.ai cloudstandard$0.37per Mtok in$0.37per Mtok outibm.com · read 2026-08-25

About

Llama Guard 3 11B Vision — a text model from Meta, sold by 2 companies from $0.35 in and $0.35 out per million tokens.

It takes text and images and returns text. The catalogue files it under guard, extract and evaluate. Two companies sell it. The cheapest is $0.35 in and $0.35 out per million tokens at IBM watsonx.

Every current figure

Maker
Meta
Register
model
Takes
text + image
Returns
text
Parameters
11 billion · read from its own name
Licence
not read
Sellers
2
Maker's own price
not read
Price
$0.35 in and $0.35 out per million tokens — IBM watsonx

Known as 1 name

llama-guard-3-11b-vision