> ## 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.

# Cerebras

> Free access to ultra-fast inference with Cerebras hardware

<Note>
  Cerebras provides free API access to various open-source models optimized for their specialized AI hardware.
</Note>

## Overview

Cerebras offers free access to multiple open-source models running on their custom AI accelerators, providing extremely fast inference speeds.

## Rate Limits

Each model has specific rate limits:

| Model Name                | Requests/Min | Tokens/Min | Requests/Hour | Tokens/Hour | Requests/Day | Tokens/Day |
| ------------------------- | ------------ | ---------- | ------------- | ----------- | ------------ | ---------- |
| gpt-oss-120b              | 30           | 60,000     | 900           | 1,000,000   | 14,400       | 1,000,000  |
| Qwen 3 235B A22B Instruct | 30           | 60,000     | 900           | 1,000,000   | 14,400       | 1,000,000  |
| Llama 3.3 70B             | 30           | 64,000     | 900           | 1,000,000   | 14,400       | 1,000,000  |
| Qwen 3 32B                | 30           | 64,000     | 900           | 1,000,000   | 14,400       | 1,000,000  |
| Llama 3.1 8B              | 30           | 60,000     | 900           | 1,000,000   | 14,400       | 1,000,000  |
| Z.ai GLM-4.6              | 10           | 60,000     | 100           | 100,000     | 100          | 1,000,000  |

## Available Models

<CardGroup cols={2}>
  <Card title="gpt-oss-120b" icon="brain">
    120B parameter open-source model
  </Card>

  <Card title="Qwen 3 235B A22B" icon="sparkles">
    Qwen's largest instruction-tuned model
  </Card>

  <Card title="Llama 3.3 70B" icon="meta">
    Meta's latest 70B model
  </Card>

  <Card title="Qwen 3 32B" icon="robot">
    Efficient 32B parameter model
  </Card>

  <Card title="Llama 3.1 8B" icon="bolt">
    Fast 8B parameter model
  </Card>

  <Card title="Z.ai GLM-4.6" icon="star">
    GLM-4 generation model
  </Card>
</CardGroup>

## API Usage

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

  client = openai.OpenAI(
      base_url="https://api.cerebras.ai/v1",
      api_key="YOUR_CEREBRAS_API_KEY"
  )

  response = client.chat.completions.create(
      model="llama3.3-70b",
      messages=[
          {"role": "user", "content": "Hello, how are you?"}
      ]
  )

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

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

  const client = new OpenAI({
      baseURL: 'https://api.cerebras.ai/v1',
      apiKey: process.env.CEREBRAS_API_KEY
  });

  const response = await client.chat.completions.create({
      model: 'llama3.3-70b',
      messages: [
          { role: 'user', content: 'Hello, how are you?' }
      ]
  });

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

  ```bash cURL theme={null}
  curl https://api.cerebras.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer YOUR_CEREBRAS_API_KEY" \
    -d '{
      "model": "llama3.3-70b",
      "messages": [
        {"role": "user", "content": "Hello, how are you?"}
      ]
    }'
  ```
</CodeGroup>

## Getting Started

<Steps>
  <Step title="Create Account">
    Sign up at [cloud.cerebras.ai](https://cloud.cerebras.ai/)
  </Step>

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

  <Step title="Start Building">
    Use the OpenAI-compatible API for inference
  </Step>
</Steps>

## Key Features

<Info>
  * Ultra-fast inference powered by Cerebras hardware
  * OpenAI-compatible API
  * Generous rate limits on free tier
  * Access to large models (up to 235B parameters)
  * High token throughput
</Info>

## Performance

<CardGroup cols={2}>
  <Card title="Fast Inference" icon="rocket">
    Specialized hardware for ultra-fast generation
  </Card>

  <Card title="Large Models" icon="expand">
    Support for models up to 235B parameters
  </Card>

  <Card title="High Throughput" icon="gauge-high">
    Up to 64,000 tokens per minute
  </Card>

  <Card title="Consistent Speed" icon="clock">
    Low latency across all model sizes
  </Card>
</CardGroup>

## Additional Resources

<CardGroup cols={2}>
  <Card title="Cerebras Cloud" icon="browser" href="https://cloud.cerebras.ai/">
    Access the platform
  </Card>

  <Card title="Documentation" icon="book" href="https://cerebras.ai/docs">
    API documentation
  </Card>
</CardGroup>