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

# Introduction

> Welcome to InfinityBlue API documentation

# InfinityBlue API

InfinityBlue is a unified, OpenAI-compatible API gateway. Send a single request format to a single endpoint and reach every major frontier model — GPT, Gemini, DeepSeek — without managing separate provider accounts, keys, or SDKs.

## What you get

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart/auth">
    Get your first request working in 5 minutes
  </Card>

  <Card title="Model Selection" icon="microchip" href="/guides/model-selection">
    Compare every supported model and pick the right one
  </Card>

  <Card title="Streaming" icon="bolt" href="/guides/streaming">
    Return tokens to users as soon as they are produced
  </Card>

  <Card title="Multimodal Input" icon="image" href="/guides/multimodal-input">
    Send images alongside text in a single turn
  </Card>
</CardGroup>

## Authentication

All requests require a Bearer token in the `Authorization` header:

```bash theme={null}
curl https://api.getinfinityblue.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

See [Authentication](/quickstart/auth) for instructions on obtaining and managing your API key.

## Supported models

The table below is a quick reference. For capability details and pricing see [Model Selection](/guides/model-selection) and the [live pricing page](https://api.getinfinityblue.com/pricing).

### Chat & reasoning

| Model                    | Provider | Notes                           |
| ------------------------ | -------- | ------------------------------- |
| `gpt-5.4`                | OpenAI   | Flagship — best overall quality |
| `gpt-5.4-mini`           | OpenAI   | Fast and cost-efficient         |
| `gpt-5.5`                | OpenAI   | Latest generation               |
| `gpt-5.3-codex`          | OpenAI   | Optimised for code tasks        |
| `gemini-3.1-pro-preview` | Google   | Long context, strong reasoning  |
| `gemini-2.5-pro`         | Google   | High-quality multimodal         |
| `gemini-2.5-flash`       | Google   | Fast and affordable             |
| `gemini-3-flash-preview` | Google   | Latest Flash generation         |
| `deepseek-v4-pro`        | DeepSeek | Advanced reasoning              |
| `deepseek-v4-flash`      | DeepSeek | Lightweight DeepSeek            |

### Image generation

| Model            | Notes                         |
| ---------------- | ----------------------------- |
| `gpt-image-2`    | OpenAI image generation       |
| `nanobanana`     | Fast image generation         |
| `nanobanana_pro` | High-quality image generation |
| `nanobanana_2`   | Latest Nano Banana generation |

### Video generation

| Model                        | Notes                       |
| ---------------------------- | --------------------------- |
| `doubao-seedance-2-0-260128` | Bytedance video generation  |
| `veo_3_1`                    | Google Veo video generation |
| `kling-v2-5-turbo`           | Kling fast video generation |

<Note>
  If you find anything missing or unclear in these docs, open an issue or PR on
  [GitHub](https://github.com/yzlltyyh/infinityblue-api-docs).
</Note>