Using Llama 3.2 90B Vision Instruct on NVIDIA NIM

Implementation guide · Llama 3.2 · AI at Meta

ServerlessOpen Weights

NVIDIA NIM exposes Llama 3.2 90B Vision Instruct through model ID meta/llama-3.2-90b-vision-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-09. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call meta/llama-3.2-90b-vision-instruct — see the documentation for request format.
  3. 3
    You'll be billed . See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

Capabilities

VisionMultimodal

About Llama 3.2 90B Vision Instruct

Instruction-tuned 90B Llama 3.2 Vision model for higher-capability image reasoning, visual question answering, visual grounding, and captioning. NVIDIA NIM lists text plus image input, text output, and a 128K context window for the Llama 3.2 Vision collection.

Full model details →

Model Specs

Released2024-09-25
Parameters88.8B
Context128k
ArchitectureDecoder Only
Knowledge cutoff2024-03

More Models on NVIDIA NIM

Llama 3.2 11B Vision InstructLlama 3.2 3B InstructLlama 3.2 1B Instruct
All models on NVIDIA NIM →

Also available on(5)

Bitdeer AI$0.15/1MVercel AI Gateway$0.72/1MFireworks AI$0.90/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States