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

# GlobalAI OPC API Reference: Endpoints and Integration

> Complete API reference for GlobalAI OPC's text, image, and video generation endpoints. Supports OpenAI, Claude, and Gemini protocol compatibility.

The GlobalAI OPC API provides REST endpoints for generating text, images, and videos using state-of-the-art AI models. All endpoints use Bearer token authentication. Whether you are building conversational applications, generating creative imagery, or producing AI-driven video content, this reference covers every endpoint, parameter, and response format you need.

## Base URLs

Use the appropriate base URL for the API category you are calling:

```
Text API:           http://apillm.globalaiopc.com/gw_llm_power
Image & Video API:  https://zcbservice.aizfw.cn/kyyReactApiServer
```

## Authentication

Include your API key as a Bearer token on every request:

```
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```

Replace `YOUR_API_KEY` with the key issued to your account. Contact GlobalAI OPC support if you need to obtain or rotate a key.

## API Categories

<CardGroup cols={2}>
  <Card title="Text APIs" icon="message" href="/api-reference/text/openai-chat">
    OpenAI-compatible chat, Claude Messages, and Gemini native endpoints for intelligent conversation and text generation.
  </Card>

  <Card title="Image APIs" icon="image" href="/api-reference/image/nano-banana-create">
    Nano Banana and GPT Image 2 endpoints for high-quality image generation from text prompts.
  </Card>

  <Card title="Video APIs" icon="video" href="/api-reference/video/sora-create">
    Nine video model families — including Sora, VEO, Seedance, Vidu, and Grok — for text-to-video and image-to-video generation.
  </Card>

  <Card title="Asset Management" icon="folder-open" href="/api-reference/assets/seedance2-asset-upload">
    Upload and manage reference media assets used as inputs for image-to-video and guided generation workflows.
  </Card>
</CardGroup>

## Video Generation Models

The table below summarises the available video models, their creation endpoints, maximum output resolution, and supported duration range.

| Model        | Endpoint                     | Max Resolution | Duration |
| ------------ | ---------------------------- | -------------- | -------- |
| Sora         | `POST /v1/sora/videos`       | 1280×720       | 4–12s    |
| VEO          | `POST /v1/veo/videos`        | 4K             | fixed    |
| Seedance 1.5 | `POST /v1/seedance/videos`   | 1080p          | 2–12s    |
| Seedance 2.0 | `POST /v1/kyyvideo2/videos`  | varies         | 4–15s    |
| Vidu         | `POST /v1/vidu/videos`       | 1080p          | 1–16s    |
| Grok         | `POST /v1/grok/videos`       | 720p           | 6–30s    |
| StarVideos   | `POST /v1/starvideos/videos` | varies         | 3–15s    |
| Videos       | `POST /v1/videos/videos`     | 720p           | 4–15s    |
| SD2 Manxue   | `POST /v1/sd2_manxue/videos` | 4K             | 4–15s    |

## Async Task Flow

Video and image generation are asynchronous. Follow these three steps after making a creation request:

1. **Create the task** — send a `POST` request to the relevant endpoint. The response returns a task `id`.
2. **Poll for status** — send `GET /v1/result/{id}` repeatedly and inspect the `status` field in the response.
3. **Retrieve the result** — when `status` is `completed`, read the `video_url` or `image_url` field to access your generated asset.

## Common Response Statuses

Every task query response includes a `status` field with one of the following values:

| Status       | Description                                             |
| ------------ | ------------------------------------------------------- |
| `queued`     | Waiting to be processed                                 |
| `processing` | Currently generating                                    |
| `completed`  | Done — result URL available                             |
| `failed`     | Generation failed — check the `error` field for details |

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/guides/quickstart">
    Get your first API call working in minutes with step-by-step instructions and copy-ready code samples.
  </Card>

  <Card title="Authentication" icon="key" href="/guides/authentication">
    Learn how to obtain your API key, set up Bearer token headers, and manage credentials securely.
  </Card>
</CardGroup>