> ## Documentation Index
> Fetch the complete documentation index at: https://docs.boostgpt.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Fireworks AI

> Use Fireworks AI models in your BoostGPT agents

## Overview

Fireworks serves open-weight models — Llama, Mixtral, Qwen, DeepSeek and Yi — behind one fast inference endpoint, so you can pick an open model without hosting it yourself.

## Available Models

<CardGroup cols={2}>
  <Card title="DeepSeek V3" icon="bolt">
    **1 credit** • Latest DeepSeek model. Improved performance and capabilities.

    * 64K context window
    * Good reasoning
    * Speed: Fast • Cost: Low
    * Model id: `deepseek-v3`
  </Card>

  <Card title="DeepSeek R1" icon="sparkles">
    **1 credit** • Specialized reasoning model. Enhanced analytical capabilities.

    * 64K context window
    * Excellent reasoning (reasoning model)
    * Speed: Medium • Cost: Low
    * Model id: `deepseek-r1`
  </Card>

  <Card title="Llama V3 (8B)" icon="zap">
    **1 credit** • Instruction-tuned 8B model. Efficient for general tasks.

    * 8K context window
    * Good reasoning
    * Speed: Very\_fast • Cost: Very\_low
    * Model id: `llama-v3-8b-instruct`
  </Card>

  <Card title="Llama V3 (70B)" icon="circle">
    **2 credits** • Large instruction-tuned model. Powerful for complex tasks.

    * 8K context window
    * Excellent reasoning
    * Speed: Medium • Cost: Medium
    * Model id: `llama-v3-70b-instruct`
  </Card>

  <Card title="Llama V3.1 (8B)" icon="gauge">
    **1 credit** • Updated 8B instruction model. Improved performance and efficiency.

    * 128K context window
    * Good reasoning
    * Speed: Very\_fast • Cost: Very\_low
    * Model id: `llama-v3p1-8b-instruct`
  </Card>

  <Card title="Llama V3.1 (70B)" icon="rocket">
    **1 credit** • Updated 70B instruction model. Enhanced capabilities and performance.

    * 128K context window
    * Excellent reasoning
    * Speed: Fast • Cost: Low
    * Model id: `llama-v3p1-70b-instruct`
  </Card>

  <Card title="Llama V3.1 (405B)" icon="star">
    **2 credits** • Massive 405B parameter model. Exceptional performance on complex tasks.

    * 128K context window
    * Exceptional reasoning
    * Speed: Slow • Cost: High
    * Model id: `llama-v3p1-405b-instruct`
  </Card>

  <Card title="Llama V3.3 (70B)" icon="brain">
    **2 credits** • Latest 70B model version. Improved instruction following and reasoning.

    * 128K context window
    * Excellent reasoning
    * Speed: Fast • Cost: Medium
    * Model id: `llama-v3p3-70b-instruct`
  </Card>

  <Card title="Yi Large" icon="wand-magic-sparkles">
    **2 credits** • Large Yi model. Strong performance across diverse applications.

    * 32K context window
    * Excellent reasoning
    * Speed: Medium • Cost: Medium
    * Model id: `yi-large`
  </Card>

  <Card title="Mixtral (8x7B)" icon="microchip">
    **1 credit** • Instruction-tuned Mixtral model. Efficient mixture of experts architecture.

    * 32K context window
    * Good reasoning
    * Speed: Fast • Cost: Low
    * Model id: `mixtral-8x7b-instruct`
  </Card>

  <Card title="Mixtral (8x22B)" icon="layer-group">
    **2 credits** • Larger instruction-tuned Mixtral. Enhanced capabilities with larger capacity.

    * 64K context window
    * Excellent reasoning
    * Speed: Medium • Cost: Medium
    * Model id: `mixtral-8x22b-instruct`
  </Card>

  <Card title="Qwen 2.5 (72B)" icon="cube">
    **1 credit** • Large Qwen model. Advanced capabilities for complex tasks.

    * 128K context window
    * Excellent reasoning
    * Speed: Medium • Cost: Medium
    * Model id: `qwen2p5-72b-instruct`
  </Card>
</CardGroup>

## Setup

### Using BoostGPT-Hosted API Keys

<Steps>
  <Step title="Select a model">
    In your BoostGPT dashboard, choose any Fireworks AI model when creating or configuring an agent.
  </Step>

  <Step title="Start chatting">
    Credits are deducted per step at the rate shown on each model above. Nothing else to configure.
  </Step>
</Steps>

### Using Your Own API Key

Bring your own key to bill Fireworks AI directly instead of spending BoostGPT credits. See
[Bring Your Own Keys](/providers/bring-your-own-keys).

```javascript theme={null}
await client.chat({
  bot_id: 'bot-id',
  message: 'Hello',
  model: 'deepseek-v3',
  provider_key: process.env.FIREWORKS_API_KEY
});
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Model Comparison" icon="chart-bar" href="/providers/model-comparison">
    Compare every model across all providers
  </Card>

  <Card title="Provider Overview" icon="layer-group" href="/providers/overview">
    See all supported providers
  </Card>
</CardGroup>