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

# Models Overview & Catalog

> Explore 60+ AI models aggregated on XRoute across Text, Image, and Video modalities with unified and native routing protocols.

Welcome to the **XRoute Model Catalog**. XRoute routes requests across global frontier models with unified billing, sub-50ms routing overhead, and vendor fallback.

To help you find the right model quickly and integrate seamlessly, our catalog is organized by **output modality** and **protocol architecture**:

> [card] [Text Models (LLMs)](https://docs.xroute.ai/resources/models/text.md)
>
> Chat & reasoning models. Supports **OpenAI Unified**, **Anthropic Unified**, and **Provider Native** formats.

> [card] [Image Models](https://docs.xroute.ai/resources/models/image.md)
>
> Text-to-image & image editing. **Native provider format only** (OpenAI, Google, Byteplus, Qwen).

> [card] [Video Models](https://docs.xroute.ai/resources/models/video.md)
>
> Text-to-video & image-to-video. **Native async task format only** (Byteplus, WAN DashScope).

***

## Modality & Protocol Support Matrix

| Output Modality | Supported Calling Protocols | Primary Endpoints | Best Use Cases |
| :- | :- | :- | :- |
| **Text Generation** | • OpenAI Unified (`/v1/chat/completions`) • Anthropic Unified (`/v1/messages`) • Native Direct (`/{Provider}/...`) | `https://api.xroute.ai/v1/chat/completions` `https://api.xroute.ai/v1/messages` `https://api.xroute.ai/{Provider}/...` | Chatbots, coding agents, structured extraction, automated reasoning |
| **Image Generation** | • **Native Provider Only** | `https://api.xroute.ai/{Provider}/images/generations` `https://api.xroute.ai/Google/image/...` | Graphic design, product mockups, game assets, marketing visuals |
| **Video Generation** | • **Native Async Tasks Only** (Create & Poll) | Create: `https://api.xroute.ai/{Provider}/.../tasks` Query: `https://api.xroute.ai/{Provider}/.../tasks/{id}` | Short video ads, character animation, film pre-visualization |

***

## Featured Models by Modality

> [tab] Text (LLMs)
>
> | Provider | Model Identifier | Context Window | Supported Protocols | Strengths |
> | :- | :- | :- | :- | :- |
> | **OpenAI** | `OpenAI/gpt-5.6-sol` | 200K | OpenAI / Anthropic / Native | Frontier enterprise reasoning, deep coding |
> | **Anthropic** | `Anthropic/claude-fable-5` | 200K | OpenAI / Anthropic / Native | Long-context understanding, high steerability |
> | **Google** | `Google/gemini-3.1-pro-preview` | 1M | OpenAI / Anthropic / Native | Massive context analysis, multimodal input |
> | **Byteplus** | `Byteplus/seed-2-0-code-preview-260328` | 128K | OpenAI / Anthropic / Native | Optimized code generation, low-latency agent tasks |
> | **Deepseek** | `Deepseek/deepseek-v4-flash` | 64K | OpenAI / Anthropic / Native | High-throughput chat, cost-effective scaling |
> | **GLM** | `GLM/glm-5` | 128K | OpenAI / Anthropic / Native | Bilingual reasoning, knowledge retrieval |
>
> 👉 [View complete Text Models guide and code samples](https://docs.xroute.ai/resources/models/text.md)

> [tab] Image
>
> | Provider | Model Identifier | Capability | Native Endpoint |
> | :- | :- | :- | :- |
> | **OpenAI** | `OpenAI/gpt-image-2.5-flare` | Text-to-Image | `POST https://api.xroute.ai/OpenAI/images/generations` |
> | **OpenAI** | `OpenAI/gpt-image-2` | Image Edit & Inpaint | `POST https://api.xroute.ai/OpenAI/images/edits` |
> | **Google** | `Google/gemini-3.1-flash-image` | Multimodal Image Gen | `POST https://api.xroute.ai/Google/image/models/{id}:generateContent` |
> | **Byteplus** | `Byteplus/seedream-5-0-260128` | High-Res Visual Synthesis | `POST https://api.xroute.ai/Byteplus/images/generations` |
> | **Qwen** | `Qwen/qwen-image-3.0-pro` | Multi-resolution Image Gen | `POST https://api.xroute.ai/Qwen/services/aigc/multimodal-generation/generation` |
>
> 👉 [View complete Image Models guide and native samples](https://docs.xroute.ai/resources/models/image.md)

> [tab] Video
>
> | Provider | Model Identifier | Resolution & Specs | Task Lifecycle |
> | :- | :- | :- | :- |
> | **Byteplus** | `Byteplus/seedance-1-5-pro-251215` | Up to 1080p, 60fps cinematic | Create: `POST .../contents/generations/tasks` Poll: `GET .../contents/generations/tasks/{task_id}` |
> | **WAN** | `WAN/wan3.0-video-prime` | High dynamic coherence, 720p/1080p | Create: `POST .../video-generation/video-synthesis` Poll: `GET .../tasks/{task_id}` |
>
> 👉 [View complete Video Models guide and async polling script](https://docs.xroute.ai/resources/models/video.md)

***

## Unified Authorization & Routing

Regardless of which model or modality you choose, all requests through XRoute use your **universal API key**:

```bash theme={null}
# Export your unified API key
export XROUTE_API_KEY="xr_live_your_key_here"
```

* Universal Gateway Base URL: `https://api.xroute.ai`
* Consolidated Billing: One credit pool covers all vendors.
* Live Real-Time Catalog: Visit [xroute.ai/en/model](https://xroute.ai/en/model) for real-time model pricing and latency statistics.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.