> ## 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.

# Providers & Models

> Choose from 50+ AI models across 9 providers—or bring your own

## Supported Providers

BoostGPT supports **9 AI providers** with **50+ models** spanning from ultra-fast nano models to advanced reasoning models.

<CardGroup cols={3}>
  <Card title="OpenAI" icon="openai" href="/providers/openai">
    GPT-4o, GPT-5, O1, O3 Mini + reasoning models
  </Card>

  <Card title="Google" icon="google" href="/providers/google">
    Gemini 2.5 Pro, Gemini 3, Flash Thinking
  </Card>

  <Card title="Anthropic" icon="anthropic" href="/providers/anthropic">
    Claude Opus 4.1, Sonnet 4.5, Extended Thinking
  </Card>

  <Card title="xAI" icon="x" href="/providers/xai">
    Grok 3, Grok 4.1, Reasoning models
  </Card>

  <Card title="DeepSeek" icon="brain" href="/providers/deepseek">
    DeepSeek V3, DeepSeek R1 (reasoning)
  </Card>

  <Card title="Mistral" icon="wind" href="/providers/mistral">
    Small, Medium, Large variants
  </Card>

  <Card title="Cohere" icon="c" href="/providers/cohere">
    Command R+, Command A, Command R7B
  </Card>

  <Card title="Groq" icon="zap" href="/providers/groq">
    Ultra-fast inference: Llama, Qwen, Mistral
  </Card>

  <Card title="Ollama" icon="server" href="/providers/ollama">
    Self-hosted local models (bring your own)
  </Card>
</CardGroup>

## Key Features

<AccordionGroup>
  <Accordion icon="key" title="Bring Your Own API Keys">
    Use your own API keys for OpenAI, Google, Anthropic, xAI, DeepSeek, Mistral, Cohere, Groq, or Ollama. You control costs and rate limits.
  </Accordion>

  <Accordion icon="cloud" title="Use Our Infrastructure (Optional)">
    Don't have API keys? Use our pooled infrastructure on paid plans. We handle provisioning, rate limits, and scaling.
  </Accordion>

  <Accordion icon="brain" title="Reasoning Models">
    Access advanced reasoning models like O1, O3 Mini, DeepSeek R1, Gemini Flash Thinking, and Claude Extended Thinking for complex problem-solving.
  </Accordion>

  <Accordion icon="gauge" title="Smart Model Selection">
    Choose models based on speed, cost, reasoning capability, and context window. Use fast models for simple queries, reasoning models for complex tasks.
  </Accordion>

  <Accordion icon="server" title="Self-Hosted with Ollama">
    Run models locally using Ollama. Keep data private, eliminate API costs, and use custom fine-tuned models.
  </Accordion>
</AccordionGroup>

## Model Categories

### Speed-Optimized (Nano/Mini)

Ultra-fast models for simple tasks, high-volume applications, and real-time responses.

**Best for:** FAQs, basic chat, high-traffic bots\
**Examples:** GPT-4.1 Nano, Llama 3.1 Instant (8B), Gemini 2.5 Flash Lite

### Balanced (Standard)

Great all-around models balancing speed, cost, and capability.

**Best for:** Most production use cases, customer support, content generation\
**Examples:** GPT-4o Mini, Claude Sonnet 4.5, Gemini 2.5 Flash

### Advanced (Pro/Large)

Powerful models for complex tasks requiring deep understanding.

**Best for:** Complex queries, creative writing, technical analysis\
**Examples:** GPT-5, Claude Opus 4.1, Gemini 2.5 Pro

### Reasoning Models

Specialized models with extended thinking for complex problem-solving.

**Best for:** Math, coding, logic puzzles, multi-step reasoning\
**Examples:** O1, DeepSeek R1, Gemini Flash Thinking, Claude Extended Thinking

[Learn more about reasoning models →](/providers/reasoning-models)

## Model Comparison

| Provider  | Model             | Speed  | Cost   | Reasoning   | Context | Credits |
| --------- | ----------------- | ------ | ------ | ----------- | ------- | ------- |
| OpenAI    | O1                | Slow   | High   | Exceptional | 200K    | 6       |
| OpenAI    | GPT-5             | Medium | High   | Exceptional | 200K    | 5       |
| OpenAI    | GPT-4o            | Medium | Medium | Excellent   | 128K    | 5       |
| OpenAI    | GPT-4o Mini       | Fast   | Low    | Good        | 128K    | 1       |
| Google    | Gemini 2.5 Pro    | Slow   | High   | Exceptional | 2M      | 3       |
| Google    | Gemini 2.5 Flash  | Fast   | Medium | Excellent   | 1M      | 2       |
| Anthropic | Claude Opus 4.1   | Medium | High   | Exceptional | 200K    | 5       |
| Anthropic | Claude Sonnet 4.5 | Medium | Medium | Excellent   | 200K    | 3       |
| xAI       | Grok 3 Reasoning  | Medium | Medium | Excellent   | 128K    | 4       |
| DeepSeek  | DeepSeek R1       | Medium | Medium | Excellent   | 64K     | 2       |
| Groq      | Llama 3.3 (70B)   | Fast   | Medium | Excellent   | 128K    | 3       |
| Ollama    | Llama 3.3 (70B)   | Medium | Free\* | Excellent   | 128K    | 2       |

\*Local hosting costs (compute) not included

[View full comparison →](/providers/model-comparison)

## Using Your Own Models (Ollama)

The **only way** to use custom models in BoostGPT is through **Ollama**.

<Steps>
  <Step title="Install Ollama">
    Download and install [Ollama](https://ollama.ai) on your server or local machine.
  </Step>

  <Step title="Pull Your Model">
    ```bash theme={null}
        ollama pull llama3.3:70b
        # Or your custom fine-tuned model
    ```
  </Step>

  <Step title="Configure BoostGPT">
    Set your Ollama host URL in the dashboard or via SDK:

    ```javascript theme={null}
        const bot = await client.chat({
          bot_id: 'my-bot-id',
          provider_host: 'http://localhost:11434',  // or your server IP
          model: 'llama3.3:70b',
          message: 'Hello, world!' 
        });
    ```
  </Step>

  <Step title="Deploy">
    Your agent will now use your self-hosted Ollama model. No API costs, full control.
  </Step>
</Steps>

[Learn more about Ollama →](/providers/ollama)

## Credits System

Each model has a **credit cost per message**. Credits are consumed when your agent generates responses.

* **Nano/Mini models:** 0.5-1 credits (cheapest)
* **Standard models:** 2-3 credits
* **Pro/Large models:** 4-5 credits
* **Reasoning models:** 3-6 credits (most expensive, but highest quality)

<Info>
  Credits are only for **agent responses**. Incoming messages, training data, and API calls don't consume credits.
</Info>

## Choosing the Right Model

### For Creators (No-Code Dashboard)

1. Go to your bot settings
2. Click "Model Selection"
3. Choose based on your needs:
   * **Fast responses** → GPT-4o Mini, Gemini Flash Lite
   * **Best quality** → GPT-5, Claude Opus, Gemini Pro
   * **Complex reasoning** → O1, DeepSeek R1
   * **Low cost** → Use nano/mini variants

### For Developers (SDK/API)

```javascript theme={null}
const bot = await client.createBot({
  name: 'Support Bot',
  model: 'gpt-5.1', // Fast & affordable
  // Or for complex queries:
  // model: 'o1', // Advanced reasoning
});
```

## Provider-Specific Setup

<CardGroup cols={2}>
  <Card title="Bring Your Own Keys" icon="key" href="/providers/bring-your-own-keys">
    Use your existing API keys from any provider
  </Card>

  <Card title="Use Our Infrastructure" icon="cloud" href="/authentication">
    Let us handle provisioning (paid plans only)
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={3}>
  <Card title="Model Comparison" icon="chart-bar" href="/providers/model-comparison">
    Compare all 50+ models
  </Card>

  <Card title="Reasoning Models" icon="brain" href="/providers/reasoning-models">
    Learn about O1, R1, etc.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Start building now
  </Card>
</CardGroup>