Multimodal
io-net
azure
github-models
vercel
Llama Family
Open Source
Released: Sep 2024 Updated: Feb 2026

Llama-3.2-90B-Vision-Instruct

Llama-3.2-90B-Vision-Instruct is a Multimodal model.

Vision
Audio
Tool Use
Reasoning
Citations

Key Specs

Context
128k
Max Output
8k
Best Price (Input / Output)
Free / Free per 1M tokens
Chat with Model

Pricing Comparison

Provider Input (1M) Output (1M) Image (1k)
github-models Free Free -
io-net $0.35 $0.40 -
vercel $0.72 $0.72 -
azure $2.04 $2.04 -

Prices are per 1 million tokens unless otherwise noted. Image pricing is per 1000 images if applicable.