Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
Help Center
Getting Started
  1. Create and verify your account to unlock full access to NVIDIA NIM APIs.
ResourcesDeveloper ForumsContact Support
FAQs
  • Terms of Use
    Privacy Policy
    Your Privacy Choices
    Contact

    Copyright © 2026 NVIDIA Corporation

    meta/llama-3.2-90b-vision-instruct

    API Reference

    Prototype

    Start building with a free API endpoint.
    import requests
    
    invoke_url = "https://integrate.api.nvidia.com/v1/chat/completions"
    stream = False
    
    headers = {
        "Authorization": "Bearer $NVIDIA_API_KEY",
        "Accept": "text/event-stream" if stream else "application/json",
    }
    
    payload = {
      "messages": [
        {
          "content": [
            {
              "image_url": {
                "url": "https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1a.jpg"
              },
              "type": "image_url"
            },
            {
              "type": "text",
              "text": "Is there a car in this image?"
            }
          ],
          "role": "user"
        }
      ],
      "model": "meta/llama-3.2-90b-vision-instruct",
      "frequency_penalty": 0,
      "max_tokens": 512,
      "presence_penalty": 0,
      "stream": stream,
      "temperature": 1,
      "top_p": 1
    }
    
    response = requests.post(invoke_url, headers=headers, json=payload, stream=stream)
    if stream:
        for line in response.iter_lines():
            if line:
                print(line.decode("utf-8"))
    else:
        print(response.json())

    Deploy

    Ready to scale? Choose your deployment path.

    Available Integrations

    Deploy this model now on your endpoint provider of choice

    Specifications

    Cutting-edge vision-Language model exceling in high-quality reasoning from images.

    • Image-Text Retrieval
    • Visual Grounding
    • Visual QA
    • image captioning
    • Image-to-Text
    Provider
    Meta
    Last Modified
    1 year ago
    Context Length
    131K
    Parameters
    89B
    Input Modalities
    Text, Image
    Output Modalities
    Text

    Model Availability

    Free Endpoint
    Available
    Partner Endpoint
    Available
    Download Available
    Available
    API calls in last 30 days
    4M