> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/cheahjs/free-llm-api-resources/llms.txt
> Use this file to discover all available pages before exploring further.

# NVIDIA NIM

> Free access to various open-source models with NVIDIA optimization

<Note>
  NVIDIA NIM provides free API access to various open-source models optimized for NVIDIA infrastructure.
</Note>

## Overview

NVIDIA NIM (NVIDIA Inference Microservices) offers free access to a variety of open-source language models optimized for high-performance inference on NVIDIA GPUs.

## Requirements

<Warning>
  **Phone Number Verification Required**: You must verify your phone number to access NVIDIA NIM.
</Warning>

## Rate Limits

| Limit Type          | Free Tier |
| ------------------- | --------- |
| Requests per minute | 40        |

<Info>
  Models tend to be context window limited on the free tier.
</Info>

## Available Models

NVIDIA NIM provides access to [various open-source models](https://build.nvidia.com/models) including:

* Llama models
* Mistral models
* Gemma models
* Qwen models
* And many more optimized open-source models

<Card title="Browse All Models" icon="grid" href="https://build.nvidia.com/models">
  Explore the full catalog of available models on NVIDIA NIM
</Card>

## API Usage

<CodeGroup>
  ```python Python theme={null}
  import openai

  client = openai.OpenAI(
      base_url="https://integrate.api.nvidia.com/v1",
      api_key="YOUR_NVIDIA_API_KEY"
  )

  response = client.chat.completions.create(
      model="meta/llama-3.3-70b-instruct",
      messages=[
          {"role": "user", "content": "Hello, how are you?"}
      ],
      max_tokens=1024
  )

  print(response.choices[0].message.content)
  ```

  ```javascript JavaScript theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
      baseURL: 'https://integrate.api.nvidia.com/v1',
      apiKey: process.env.NVIDIA_API_KEY
  });

  const response = await client.chat.completions.create({
      model: 'meta/llama-3.3-70b-instruct',
      messages: [
          { role: 'user', content: 'Hello, how are you?' }
      ],
      max_tokens: 1024
  });

  console.log(response.choices[0].message.content);
  ```

  ```bash cURL theme={null}
  curl https://integrate.api.nvidia.com/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer YOUR_NVIDIA_API_KEY" \
    -d '{
      "model": "meta/llama-3.3-70b-instruct",
      "messages": [
        {"role": "user", "content": "Hello, how are you?"}
      ],
      "max_tokens": 1024
    }'
  ```
</CodeGroup>

## Getting Started

<Steps>
  <Step title="Create Account">
    Visit [build.nvidia.com](https://build.nvidia.com/explore/discover)
  </Step>

  <Step title="Verify Phone Number">
    Complete phone number verification
  </Step>

  <Step title="Generate API Key">
    Create an API key from your dashboard
  </Step>

  <Step title="Start Building">
    Use the OpenAI-compatible API to access models
  </Step>
</Steps>

## Limitations

<Warning>
  * Context windows may be limited compared to paid tiers
  * 40 requests per minute across all models
  * Phone verification required for access
</Warning>

## Additional Resources

<CardGroup cols={2}>
  <Card title="NVIDIA NIM" icon="rocket" href="https://build.nvidia.com/explore/discover">
    Access the platform
  </Card>

  <Card title="Model Catalog" icon="database" href="https://build.nvidia.com/models">
    Browse available models
  </Card>
</CardGroup>