Overview

Infron is a unified AI platform that provides access to 500+ state-of-the-art models for image generation, video creation, audio synthesis, and more.

What You Can Create

Image Generation

Category	Description
Text to Image	Generate images from text prompts
Image to Image	Edit, transform, or style transfer images
Upscaler	Enhance resolution and image quality
AI Remover	Remove objects, backgrounds, or watermarks

Video Generation

Category	Description
Image to Video	Animate still images into video
Text to Video	Create videos from text descriptions
Video Effects	Apply visual effects and filters
Video to Video	Edit, restyle, or enhance videos
Video Extend	Extend video duration seamlessly
Motion Control	Control movement and animation

Audio & Speech

Category	Description
Text to Speech	Generate natural voice from text
Text to Audio	Create music and sound effects
Speech to Text	Transcribe audio to text
Audio Editing	Edit and enhance audio files
Video to Audio	Generate audio/music for videos

Digital Human & Portrait

Category	Description
Digital Human	Create talking avatar videos
Portrait Transfer	Face swap and portrait editing

3D Generation

Category	Description
Image to 3D	Generate 3D models from images
Text to 3D	Create 3D models from text

AI Vision & Analysis

Category	Description
Image to Text	Image captioning and analysis
Content Moderation	Filter inappropriate content
Video to Text	Video understanding and captioning

Request Flow

1. Submit Task

Send your request with parameters to the model endpoint:

cURL (Video Generation)

curl https://llm.onerouter.pro/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "{model-id}",
  "prompt": "Your prompt here"
  ...parameters
}'

cURL (Image Generation)

2. Task Processing

• Validates your request

• Routes to the appropriate model

• Routes to the fallback providers, if the previous provider experienced issues such as insufficient capacity and availability failures.

• Queues and processes the task

• Generates content

3. Retrieve Results

Poll the task status until completion:

cURL (Video Generation)

curl https://video.onerouter.pro/v1/videos/tasks/{task_id} \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" 

cURL (Image Generation)

When status is completed, the outputs array contains URLs to your generated content.

JSON (Video Generation)

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "object": "video",
    "model": "{model-id}",
    "status": "completed",
    "fail_reason": "",
    "submit_time": 1779064285,
    "start_time": 1779064284,
    "finish_time": 1779064332,
    "outputs": [
      "https://storage.googleapis.com/infron_gcs/video%2Fvideo_v2%2Fveo_output%2Fe79e79099e6544138c8d2db68bcca266%2F16093903391301042331%2Fsample_0.mp4"
    ],
    "created_at": "2026-05-18 00:31:25"
  }
}

JSON (Image Generation)

Content Lifecycle

1. Task created — Your request is received

2. Processing — AI model generates content

3. Completed — Content available via URLs

4. Retained for 7 days — Download before expiration

5. Deleted — Content is permanently removed

created -> in_progress → processing → completed | failed

Rate Limits

Your account tier determines:

• How many requests per minute

• How many concurrent tasks

See Account Levels & Rate Limits for details.