Parameter Specification

Unified API parameters for seamless model switching

APIXO standardizes parameters across all models within each category. Switch from Flux 2 to Midjourney with minimal code changes — 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"
  }
}

Top-Level Parameters

provider · string · default: "auto"

Routing strategy. Options: auto (best balance), value (cost-optimized), official (direct provider).

request_type · string · default: "async"

How to receive results. async for polling, callback for webhook delivery.

callback_url · string

Webhook URL for receiving results. Required when request_type is callback. Must be a publicly accessible HTTPS endpoint.

input · object · required

Model-specific generation parameters. Structure varies by model category (image, video, audio).

---

Image Generation Parameters

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

input · object · required

Show properties

mode · string · default: "text-to-image" · required

Generation mode: text-to-image or image-to-image.

prompt · string · required

Text description of the desired output. 1–5000 characters.

negative_prompt · string

Elements to avoid in the generated image (e.g., "blurry, low quality").

image_urls · string[]

Reference image URLs for image-to-image mode. Max 5 images, each under 10 MB.

aspect_ratio · string · default: "1:1"

Output aspect ratio: 1:1, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 9:16, 16:9, 21:9, or auto.

resolution · string · default: "2K"

Output resolution: 1K, 2K, or 4K.

output_format · string · default: "png"

Output format: png (lossless, larger) or jpeg (compressed, smaller).

---

Video Generation Parameters

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

input · object · required

Show properties

mode · string · default: "text-to-video" · required

Generation mode: text-to-video or image-to-video.

prompt · string · required

Text description of the desired video content.

negative_prompt · string

Elements to avoid in the generated video (e.g., "shaky, low quality").

image_urls · string[]

Reference image URLs for image-to-video mode.

aspect_ratio · string · default: "16:9"

Output aspect ratio: 1:1, 16:9, or 9:16.

resolution · string · default: "1080p"

Output resolution: 480p, 720p, or 1080p.

duration · integer

Video length in seconds.

sound · boolean · default: "false"

Whether to generate audio alongside the video.

---

Audio Generation Parameters

Audio models (Suno) use these input parameters:

input · object · required

Show properties

mode · string · required

Suno version: V4, V4_5, V4_5PLUS, or V5.

prompt · string · required

Lyrics or a description of the desired music.

customMode · boolean · default: "false"

Enable custom mode for full control over style and lyrics.

instrumental · boolean · default: "false"

Generate instrumental only (no vocals).

---

Aspect Ratio Reference

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

{
  "provider": "auto",
  "request_type": "async",
  "input": {
    "mode": "text-to-image",
    "prompt": "a serene mountain landscape at sunset",
    "aspect_ratio": "16:9",
    "resolution": "2K"
  }
}

Video

{
  "provider": "auto",
  "request_type": "callback",
  "callback_url": "https://your-server.com/callback",
  "input": {
    "mode": "text-to-video",
    "prompt": "a drone shot flying over mountains",
    "aspect_ratio": "16:9",
    "duration": 10
  }
}

Audio

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

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

---

Related

• Generate Task
• Status Task
• Models