taskId, then poll for completion or receive a webhook callback. A small number of lightweight models may return final results directly; their individual pages call that out explicitly.
Base URL
Request flow
| Step | Endpoint | Purpose |
|---|---|---|
| 1 | POST /generateTask/{model} | Submit a generation task |
| 2 | GET /statusTask/{model}?taskId={id} | Poll task status and retrieve results |
| Optional | callback_url in the request body | Receive webhook delivery instead of polling |
Start here
Generate Task
Submit an image, video, or audio generation task.
Status Task
Poll for task progress, final results, and failures.
Webhooks
Receive task completion callbacks in production.
Parameter Specification
Compare common request fields across models.
Model categories
Image Models
Generate images, edit references, upscale, and create variations.
Video Models
Generate videos from text, images, first and last frames, or references.
Audio Models
Generate music, speech, and voice outputs.
LLM Gateway
Looking for Claude, OpenAI, or Gemini compatible APIs? Use the LLM Gateway.
Browse by provider
| Category | Provider or family | Models |
|---|---|---|
| Image | Nano Banana, Nano Banana Pro, Nano Banana 2 | |
| Image | OpenAI | GPT Image 1, GPT Image 2 |
| Image | xAI | Grok Image |
| Image | Black Forest Labs | Flux 2, Flux Kontext |
| Image | Midjourney | Midjourney |
| Image | Runway | Runway Gen4 Image, Runway Gen4 Image Turbo |
| Image | ByteDance | Seedream 4.0, Seedream 4.5, Seedream 5.0, Seedream 5.0 Pro |
| Image | Alibaba | Wan 2.5 Image, Wan 2.6 Image, Wan 2.7 Image |
| Image | APIXO | Image Upscaler, Image Watermark Remover |
| Video | OpenAI | Sora 2, Sora 2 Pro |
| Video | Runway | Runway Gen4 Video Turbo |
| Video | Veo 3.1 (including Extend modes), Gemini Omni | |
| Video | Alibaba | Wan 2.2 Animate, Wan 2.5, Wan 2.6, Wan 2.7, HappyHorse |
| Video | ByteDance | Seedance 1.5 Pro (including Video Extend mode), Seedance 2.0, Seedance 2.0 Fast |
| Video | Kuaishou | Kling 2.1, Kling 2.5 Turbo Pro, Kling 2.6, Kling 3.0 |
| Video | MiniMax / Hailuo | Hailuo 2.3, Hailuo 2.3 Fast |
| Video | Vidu, LTX, Avatar | Vidu Q3, LTX 2 19B, InfiniteTalk |
| Audio | Suno | Suno |
| Audio | Alibaba | CosyVoice 3 Flash, CosyVoice 3 Plus, CosyVoice 3.5 Flash, CosyVoice 3.5 Plus |
| Audio | MiniMax | MiniMax Speech 2.8, MiniMax Voice |
Choosing a generation model
| Goal | Good starting point |
|---|---|
| Fast image prototype | Nano Banana |
| Higher-quality image generation | Flux 2, GPT Image 2, Seedream 4.0, Seedream 5.0, Seedream 5.0 Pro |
| Artistic image generation | Midjourney |
| Reference-guided image generation | Runway Gen4 Image, Runway Gen4 Image Turbo |
| Alibaba image generation and editing | Wan 2.7 Image |
| Image upscaling | Image Upscaler |
| Watermark cleanup | Image Watermark Remover |
| Text-to-video | Sora 2, Veo 3.1, Gemini Omni, Wan 2.5 |
| Image-to-video | Runway Gen4 Video Turbo, Sora 2 Pro, Hailuo 2.3, Kling 2.6 |
| Music generation | Suno |
| Text-to-speech or voice cloning | CosyVoice 3.5 Plus, MiniMax Speech 2.8, MiniMax Voice |
From playground to API
If you came here from an APIXO model playground, open the matching model page in the sidebar. Each model page includes:- Model ID and endpoints
- A copy-paste request
- Supported request parameters
- Response and result format
- Polling, webhook, error, and retry guidance
Pricing is maintained on the Pricing page. Use it as the source of truth for current model prices and route differences.