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

AIReiter is a unified AI content generation API platform that provides text dialogue, image generation, and video generation services. By simple REST API calls, you can use mainstream AI models such as Claude, GPT, Gemini, Sora2, VEO3, Seedance2, and others. The text interface is fully compatible with the OpenAI SDK and can be used by directly replacing the baseURL.

Quick Start

Text Chat

Compatible with OpenAI SDK, supports Claude, GPT, and other models

Image Generation

Generate images using GPT-4o, Gemini, Seedream, and other models

Video Generation

Generate video content using Sora2, VEO3, Seedance2, and other models

Task Status Query

Query execution status and results of asynchronous tasks

Check Balance

Check points balance and remaining free quota for each model

Get API Key

Access the console to get your API Key

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:

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:

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:

{
  "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 offers 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

Channels only affect service stability and do not impact output quality. All channels use the same underlying model, ensuring identical quality of generated results. Generally, higher-priced channels provide better service stability.

When using, simply replace the model name with the corresponding channel version, for example, replace "sora2" with "sora2_plus", while keeping other parameters unchanged.

Supported Models

Text Chat Series

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

OpenAI Chat Completions API

Compatible with OpenAI SDK, supports GPT, Claude, and other models

OpenAI Responses API

OpenAI’s latest Responses format

Claude Messages API

Anthropic native Messages API format

Image Generation Series

AIReiter provides various image generation models, supporting text-to-image and image-to-image functions:

GPT-4o Image

OpenAI’s high-quality image generation model

Gemini-2.5-Flash (Nano banana)

Google’s latest fast image generation model

Gemini-3-Pro (Nano banana pro)

Google professional-grade image generation model

Nano Banana V2

Supports multiple generation modes including text-to-image, image-to-image, and image editing

Seedream-4.0

Efficient image generation solution

Seedream-4.5

Seedream version 4.5

Seedream V5 lite

Seedream latest version, supports internet-enhanced generation

Video Generation Series

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

Sora2

OpenAI Sora2 video generation model (10-15 seconds)

Sora2 Pro

Sora2 professional edition, supports HD resolution

VEO3.1

Google VEO3.1 video generation model

VEO3.1 Fast

VEO3.1 fast version

Seedance-1.5-pro

Supports start and end frame control and audio generation (4-12 seconds)

Seedance Pro Fast

Seedance fast version, supports start frame control

Seedance Pro

Seedance professional edition, supports start and end frame control

Seedance 2.0

Supports multiple reference images, reference videos, and start/end frame control (4-15 seconds)

Seedance 2.0 Fast

Seedance 2.0 fast version, supports multiple reference images and start/end frame control

Core Features

Asynchronous Task Processing

All generation requests use an asynchronous processing mode to avoid long waiting times:

You need to provide out_task_id (initiator’s task ID, used for business identification) when submitting tasks
The submitted out_task_id is returned immediately
You can query the task status using the out_task_id
Supports webhook callback notifications (optional)
Task status is updated in real time: pending → processing → completed

Multi-model Support

A unified API endpoint supporting various text, image, and video generation models:

Text conversation: Claude, GPT and other models, compatible with OpenAI SDK
Image generation: GPT-4o, Gemini, Seedream and other models
Video generation: Sora2, VEO3, Seedance and other models
Unified request format and response structure
Flexible parameter configuration

Transparent Pricing

Charged by points, transparent and clear:

Each task returns the estimated consumed points
Actual consumed points are shown after task completion
Pay only for successfully generated content
No hidden fees

Flexible Configuration

Supports multiple generation parameter configurations:

Image: Various aspect ratios (1:1, 3:2, 2:3)
Video: Various aspect ratios (16:9, 9:16), durations (10 seconds, 15 seconds), 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 API Key Management Page to obtain your API key.

FAQ

How to get an API Key?

Visit the API Key Management page, log in to create and manage your API Keys.

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.

How to query task status?

Use the task status query API and pass your custom out_task_id:

POST https://aireiter.com/api/openapi/query

See the Task Status Query Documentation for details.

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

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

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

Next Steps

View Text Conversation Documentation

Learn how to use the text conversation API

View Image Generation Documentation

Learn how to use various image generation models

View Video Generation Documentation

Learn how to generate video content

Task Management

Learn how to manage and query task statuses

Get API Key

Start using AIReiter now

Overview

Image Series

Video Series

Task Management

​Quick Start

Text Chat

Image Generation

Video Generation

Task Status Query

Check Balance

Get API Key

​API Workflow

​1. Submit Generate Task

​2. Query Task Status

​3. Get Generate Result

​Model Channels

​Supported Models

​Text Chat Series

OpenAI Chat Completions API

OpenAI Responses API

Claude Messages API

​Image Generation Series

GPT-4o Image

Gemini-2.5-Flash (Nano banana)

Gemini-3-Pro (Nano banana pro)

Nano Banana V2

Seedream-4.0

Seedream-4.5

Seedream V5 lite

​Video Generation Series

Sora2

Sora2 Pro

VEO3.1

VEO3.1 Fast

Seedance-1.5-pro

Seedance Pro Fast

Seedance Pro

Seedance 2.0

Seedance 2.0 Fast

​Core Features

​Asynchronous Task Processing

​Multi-model Support

​Transparent Pricing

​Flexible Configuration

​Authentication Method

​FAQ

​Next Steps

View Text Conversation Documentation

View Image Generation Documentation

View Video Generation Documentation

Task Management

Get API Key

Quick Start

API Workflow

1. Submit Generate Task

2. Query Task Status

3. Get Generate Result

Model Channels

Supported Models

Text Chat Series

Image Generation Series

Video Generation Series

Core Features

Asynchronous Task Processing

Multi-model Support

Transparent Pricing

Flexible Configuration

Authentication Method

FAQ

Next Steps