Parameter Specification

Unified API parameters for seamless model switching

Why Unified Parameters?

APIXO standardizes API parameters across all models within each category. This means:

Seamless model switching — Change from Flux 2 to Midjourney with minimal code changes
Consistent experience — Same parameter names and types across similar models
Faster integration — Learn once, use everywhere

Request Structure

All generation models follow the same request structure:

{
  "provider": "auto",
  "request_type": "async",
  "callback_url": "https://your-server.com/callback",
  "input": {
    "mode": "text-to-image",
    "prompt": "your description",
    // ... other parameters
  }
}

Top-Level Parameters

Parameter	Type	Default	Description
`provider`	string	`auto`	Routing: `auto`, `value`, or `official`
`request_type`	string	`async`	`async` (polling) or `callback` (webhook)
`callback_url`	string	—	Required when `request_type=callback`
`input`	object	—	Model input parameters

Image Generation Parameters

All image models (Flux 2, Midjourney, GPT Image 1, etc.) share these common parameters:

{
  "input": {
    "mode": "text-to-image",
    "prompt": "a serene mountain landscape at sunset",
    "negative_prompt": "blurry, low quality",
    "image_urls": ["https://..."],
    "aspect_ratio": "16:9",
    "resolution": "2K",
    "output_format": "png"
  }
}

Parameter	Type	Description
`mode`	string	`text-to-image` or `image-to-image`
`prompt`	string	Text description for generation
`negative_prompt`	string	Elements to avoid
`image_urls`	string[]	Reference images (for image-to-image)
`aspect_ratio`	string	`1:1`, `16:9`, `9:16`, `4:3`, `3:4`, etc.
`resolution`	string	`1K`, `2K`, or `4K`
`output_format`	string	`png` or `jpeg`

Video Generation Parameters

All video models (Sora 2, Kling, Veo, etc.) share these common parameters:

{
  "input": {
    "mode": "text-to-video",
    "prompt": "a drone shot flying over mountains",
    "negative_prompt": "shaky, low quality",
    "image_urls": ["https://..."],
    "aspect_ratio": "16:9",
    "resolution": "1080p",
    "duration": 10,
    "sound": true
  }
}

Parameter	Type	Description
`mode`	string	`text-to-video` or `image-to-video`
`prompt`	string	Text description for generation
`negative_prompt`	string	Elements to avoid
`image_urls`	string[]	Reference images (for image-to-video)
`aspect_ratio`	string	`1:1`, `16:9`, `9:16`
`resolution`	string	`480p`, `720p`, or `1080p`
`duration`	integer	Video length in seconds
`sound`	boolean	Whether to generate audio

Audio Generation Parameters

Audio models (Suno) use these parameters:

{
  "input": {
    "mode": "V4_5PLUS",
    "prompt": "upbeat pop song about summer",
    "customMode": false,
    "instrumental": false
  }
}

Parameter	Type	Description
`mode`	string	Version: `V4`, `V4_5`, `V4_5PLUS`, `V5`
`prompt`	string	Lyrics or music description
`customMode`	boolean	Custom mode with full control
`instrumental`	boolean	Instrumental only (no vocals)

Aspect Ratio Reference

Supported across most models:

Value	Description	Best For
`1:1`	Square	Social media, avatars
`16:9`	Widescreen	Video, desktop wallpapers
`9:16`	Vertical	Mobile, short videos
`4:3`	Classic	Traditional photos
`3:4`	Portrait	Classic portraits
`21:9`	Ultra-wide	Cinematic, banners

Quick Reference

// Image Generation
{
  "provider": "auto",
  "request_type": "async",
  "input": {
    "mode": "text-to-image",
    "prompt": "...",
    "aspect_ratio": "16:9",
    "resolution": "2K"
  }
}
 
// Video Generation
{
  "provider": "auto",
  "request_type": "callback",
  "callback_url": "https://...",
  "input": {
    "mode": "text-to-video",
    "prompt": "...",
    "aspect_ratio": "16:9",
    "duration": 10
  }
}
 
// Audio Generation
{
  "provider": "auto",
  "request_type": "async",
  "input": {
    "mode": "V4_5PLUS",
    "prompt": "...",
    "customMode": false,
    "instrumental": false
  }
}

Some models have additional unique parameters for advanced features. See individual model documentation for details.

Parameter Specification

On this page