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

# AIReiter — AI Text, Image, and Video Generation API Platform

> A unified AI text, image, and video generation API platform. Supports multiple mainstream models, including Claude, GPT, Gemini, VEO3, Seedance2, and more. Compatible with the OpenAI SDK, asynchronous task processing, transparent pricing, simple and easy to use.

export const apiKeyUrl = 'https://aireiter.com/keys';

AIReiter is a unified AI content generation API platform that provides text conversation, image generation, and video generation services. With simple REST API calls, you can use a variety of mainstream AI models such as Claude, GPT, Gemini, VEO3, and Seedance2. The text interface is fully compatible with the OpenAI SDK and can be used by directly replacing `baseURL`.

## Quick Start

<CardGroup cols={2}>
  <Card title="Text Chat" icon="message" href="/en/api-reference/text/openai-chat-completions-api/endpoint">
    Compatible with the OpenAI SDK, supports Claude, GPT, and other models
  </Card>

  <Card title="Image Generation" icon="image" href="/en/api-reference/images/gpt-4o/generation">
    Generate images using models such as GPT-4o, Gemini, and Seedream
  </Card>

  <Card title="Video Generation" icon="video" href="/en/api-reference/videos/veo3-1/generation">
    Generate video content using models such as VEO3 and Seedance2
  </Card>

  <Card title="Task Status Query" icon="list-check" href="/en/api-reference/tasks/status">
    Query the execution status and results of asynchronous tasks
  </Card>

  <Card title="Check Balance" icon="wallet" href="/en/api-reference/tasks/balance">
    Check your token balance and the remaining free quota for each model
  </Card>

  <Card title="Get API Key" icon="key" href={apiKeyUrl}>
    Access the console to get your API Key
  </Card>
</CardGroup>

## API Workflow

### 1. Submit Generate Task

All image and video generation uses asynchronous processing. When submitting a task, you need to provide `out_task_id` (initiator's task ID), and the system will return the same `out_task_id`:

```bash theme={null}
curl --request POST \
  --url https://aireiter.com/api/openapi/submit \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt_4o",
    "params": {
      "prompt": "A cute cat in the garden",
      "aspect_ratio": "1:1"
    },
    "out_task_id": "my_task_123456"
  }'
```

### 2. Query Task Status

Use the `out_task_id` you submitted to check the task progress and results:

```bash theme={null}
curl --request POST \
  --url https://aireiter.com/api/openapi/query \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "out_task_id": "my_task_123456"
  }'
```

### 3. Get Generate Result

After the task is completed, the response will include URLs of the generated images or videos:

```json theme={null}
{
  "statusCode": 200,
  "message": "",
  "data": {
    "out_task_id": "my_task_123456",
    "status": "completed",
    "output": [
      {
        "url": "https://s1.pxz.ai/upload/image-generator/xxx.jpeg"
      }
    ]
  }
}
```

## Model Channels

Model channels represent different service tiers. Each model can provide multiple channel versions, divided into four levels:

| Channel | Description |
| - | - |
| `base` | Basic version, lowest price |
| `plus` | Enhanced version |
| `advanced` | Advanced version |
| `max` | Flagship version, highest stability |

<Note>
  The channel only affects service stability, not output quality. All channels use the same underlying model, and the quality of the generated results is exactly the same. Generally speaking, the higher the channel price, the better the service stability.
</Note>

When using it, just replace the model name with the corresponding channel version. For example, replace `"seedance2"` with `"seedance2_fast"`, and keep the other parameters unchanged.

## Supported Models

### Text Chat Series

Compatible with OpenAI Chat Completions API and Responses API, supporting multi-turn conversations, tool calling, structured outputs, and streaming responses:

<CardGroup cols={2}>
  <Card title="OpenAI Chat Completions API" icon="message" href="/en/api-reference/text/openai-chat-completions-api/endpoint">
    Compatible with OpenAI SDK, supporting models such as GPT and Claude
  </Card>

  <Card title="OpenAI Responses API" icon="message" href="/en/api-reference/text/openai-responses-api/endpoint">
    OpenAI's latest Responses format
  </Card>

  <Card title="Claude Messages API" icon="message" href="/en/api-reference/text/claude-messages-api/endpoint">
    Anthropic native Messages API format
  </Card>

  <Card title="Jev" icon="message" href="/en/api-reference/text/jev/endpoint">
    Synchronous decision API. Submit materials and true/false questions to return probabilities, options, or scores
  </Card>
</CardGroup>

### Image Generation Series

AIReiter provides multiple image generation models, supporting text-to-image and image-to-image features:

<CardGroup cols={2}>
  <Card title="GPT-4o Image" icon="image" href="/en/api-reference/images/gpt-4o/generation">
    OpenAI's high-quality image generation model
  </Card>

  <Card title="GPT-Image-2" icon="image" href="/en/api-reference/images/gpt-image-2/generation">
    Supports text-to-image / image-to-image, 13 aspect ratios, and up to 9 reference images
  </Card>

  <Card title="GPT-Image-2.5" icon="image" href="/en/api-reference/images/gpt-image-2-5/generation">
    Flare / Sunburst tiers, text-to-image and reference image editing, 1K to 4K
  </Card>

  <Card title="Gemini-2.5-Flash (Nano banana)" icon="image" href="/en/api-reference/images/nano-banana/generation">
    Google's latest fast image generation model
  </Card>

  <Card title="Gemini-3-Pro (Nano banana pro)" icon="image" href="/en/api-reference/images/gemini-3-pro/generation">
    Google's professional-grade image generation model
  </Card>

  <Card title="Nano Banana V2" icon="image" href="/en/api-reference/images/nano-banana-v2/generation">
    Supports multiple generation modes including text-to-image, image-to-image, and image editing
  </Card>

  <Card title="Seedream-4.0" icon="image" href="/en/api-reference/images/seedream-4/generation">
    Efficient image generation solution
  </Card>

  <Card title="Seedream-4.5" icon="image" href="/en/api-reference/images/seedream-4.5/generation">
    Seedream version 4.5
  </Card>

  <Card title="Seedream V5 lite" icon="image" href="/en/api-reference/images/seedream-v5-lite/generation">
    Latest version of Seedream, supporting web search-enhanced generation
  </Card>
</CardGroup>

### Video Generation Series

Supports text-to-video and image-to-video, providing multiple resolution and duration options:

<CardGroup cols={2}>
  <Card title="VEO3.1" icon="video" href="/en/api-reference/videos/veo3-1/generation">
    Google VEO3.1 video generation model
  </Card>

  <Card title="VEO3.1 Fast" icon="video" href="/en/api-reference/videos/veo3-1-fast/generation">
    VEO3.1 Fast version
  </Card>

  <Card title="Seedance-1.5-pro" icon="video" href="/en/api-reference/videos/seedance-1-5-pro/generation">
    Supports first-and-last frame control and audio generation (4-12 seconds)
  </Card>

  <Card title="Seedance Pro Fast" icon="video" href="/en/api-reference/videos/seedance_pro_fast/generation">
    Seedance fast version, supporting first frame control
  </Card>

  <Card title="Seedance Pro" icon="video" href="/en/api-reference/videos/seedance_pro/generation">
    Seedance Pro version, supporting first-and-last frame control
  </Card>

  <Card title="Seedance 2.0" icon="video" href="/en/api-reference/videos/seedance2/generation">
    Supports multi-reference images, reference videos, and first-and-last frame control (4-15 seconds)
  </Card>

  <Card title="Seedance 2.0 Fast" icon="video" href="/en/api-reference/videos/seedance2_fast/generation">
    Seedance 2.0 fast version, supporting multi-reference images and first-and-last frame control
  </Card>
</CardGroup>

## Core Features

### Asynchronous Task Processing

All generation requests use asynchronous processing to avoid long waits:

* When submitting a task, you must pass in `out_task_id` (the initiator's task ID, used for business identification)
* Immediately returns the `out_task_id` you submitted
* You can use `out_task_id` to query the task status
* Supports webhook callback notifications (optional)
* Real-time task status updates: `pending` → `processing` → `completed`

### Multi-Model Support

A unified API endpoint that supports multiple text, image, and video generation models:

* **Text Conversation**: Models such as Claude and GPT, compatible with the OpenAI SDK
* **Image Generation**: Models such as GPT-4o, Gemini, and Seedream
* **Video Generation**: Models such as VEO3 and Seedance
* Unified request format and response structure
* Flexible parameter configuration

### Transparent Pricing

Billed by credits, with clear and transparent pricing:

* Each task returns the estimated credit consumption
* The actual credit consumption is shown after the task is completed
* You only pay for successfully generated content
* No hidden fees

### Flexible Configuration

Supports multiple generation parameter configurations:

* **Images**: Multiple aspect ratios (1:1, 3:2, 2:3)
* **Video**: Multiple aspect ratios (16:9, 9:16), durations (10 seconds, 15 seconds), and resolutions
* Supports reference images (image-to-image, image-to-video)

## Authentication Method

All API requests require authentication using a Bearer Token:

```
Authorization: Bearer YOUR_API_KEY
```

**Get API Key:**

Visit the <a href={apiKeyUrl} target="_blank">API Key Management Page</a> to obtain your API key.

## FAQ

<AccordionGroup>
  <Accordion title="How to get an API Key?">
    Visit the <a href={apiKeyUrl} target="_blank">API Key Management page</a>, log in to create and manage your API Keys.
  </Accordion>

  <Accordion title="How long does image and video generation take?">
    All generation tasks are processed asynchronously. Image generation usually takes a few seconds to tens of seconds. Video generation typically takes 1-5 minutes depending on duration and resolution. After submitting the task you will immediately get an out\_task\_id, which can be used to track progress via the status query API.
  </Accordion>

  <Accordion title="How to query task status?">
    Use the task status query API and pass your custom `out_task_id`:

    ```bash theme={null}
    POST https://aireiter.com/api/openapi/query
    ```

    See the [Task Status Query Documentation](/en/api-reference/tasks/status) for details.
  </Accordion>

  <Accordion title="What is out_task_id?">
    `out_task_id` is a client-generated task ID, set by you when submitting a task:

    * **Required parameter**: You must include `out_task_id` when submitting a task
    * **Business identifier**: Can be your system’s order number, business ID, etc.
    * **Flexible query**: Use `out_task_id` directly to query task status
    * **Result association**: The query result will include `out_task_id` to help you correlate business data
  </Accordion>

  <Accordion title="How is billing calculated?">
    AIReiter uses a credit-based billing system:

    * Estimated credit consumption (`estimated_credits`) is returned when submitting a task
    * Actual credit consumption (`credits_used`) is returned when the task is completed
    * Only pay for successfully generated content; failed tasks are free
    * Different models consume different amounts of credits
  </Accordion>

  <Accordion title="What image and video formats are supported?">
    * **Images**: Supports common formats like JPEG, PNG
    * **Videos**: Outputs in MP4 format
    * **Reference images**: Accepts publicly accessible image URLs as input
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="View Text Chat Documentation" icon="message" href="/en/api-reference/text/openai-chat-completions-api/endpoint">
    Learn how to use the text chat API
  </Card>

  <Card title="View Image Generation Documentation" icon="image" href="/en/api-reference/images/gpt-4o/generation">
    Learn how to use various image generation models
  </Card>

  <Card title="View Video Generation Documentation" icon="video" href="/en/api-reference/videos/veo3-1/generation">
    Learn how to generate video content
  </Card>

  <Card title="Task Management" icon="list-check" href="/en/api-reference/tasks/status">
    Learn how to manage and query task status
  </Card>

  <Card title="Get API Key" icon="key" href={apiKeyUrl}>
    Start using AIReiter now
  </Card>
</CardGroup>