Skip to main content

Unified Access

We prioritize providing a OpenAI-compatible format. Existing applications built on OpenAI SDK or HTTP usually only need to replace the Base URL and API keys.

Multi-Protocol Video Support

Also exposes /v1/videos, Seedance native format, Omni, and Veo format specifications, as well as video APIs dedicated to certain models.

Imaging Capabilities

We provide OpenAI image generation and editing endpoints, while retaining model-specific formats such as Gemini image generation.

Music Generation

Provides music generation task APIs, supporting prompt-based descriptions, light music/instrumental-only, and advanced lyrics mode, with results queried by task ID.

Long-Running Task Query

Video, music, and some generation tasks are queried uniformly by task ID, response id, or operation name, making them suitable for asynchronous integration and polling.

​
Overview of Currently Public Capabilities

​
Text and Response

  • POST /v1/chat/completions
  • POST /v1/responses

​
Image

  • POST /v1/images/generations
  • POST /v1/images/edits
  • POST /v1beta/models/{model}:generateContent

​
Music

  • POST /suno/submit/music
  • GET /suno/fetch/{task_id}

​
Video

  • POST /v1/videos
  • GET /v1/videos/{task_id}
  • POST /api/v3/contents/generations/tasks
  • GET /api/v3/contents/generations/tasks/{task_id}
  • POST /api/v1/services/aigc/video-generation/video-synthesis
  • GET /api/v1/tasks/{task_id}
  • POST /ent/v2/text2video
  • POST /ent/v2/img2video
  • POST /ent/v2/start-end2video
  • POST /ent/v2/reference2video
  • GET /ent/v2/tasks/{task_id}/creations
  • POST /v1beta/models/{model}:predictLongRunning
  • GET /v1beta/{operation_name}
  • Model-specific video endpoints such as Kling

​
Currently Public Model Families

​
Nano Banana

  • 7 public models in total
  • nano-banana、nano-banana-2、nano-banana-2-2k、nano-banana-2-4k、nano-banana-pro、nano-banana-pro-2k、nano-banana-pro-4k

​
Sora

  • 2 public models in total
  • sora-2、sora-2-pro

​
Gemini Omni

  • 1 public model in total
  • gemini-omni

​
HappyHorse

  • A total of 5 public models
  • happyhorse-1.0、happyhorse-1.0-i2v、happyhorse-1.0-t2v、happyhorse-1.0-r2v、happyhorse-1.0-video-edit

​
Veo

  • 12 public models in total
  • veo3、veo3-fast、veo3-fast-frames、veo3-frames、veo3-pro、veo3-pro-frames、veo3.1、veo3.1-4k、veo3.1-components、veo3.1-fast、veo3.1-pro、veo3.1-pro-4k

​
Grok

  • 3 public models in total
  • grok-imagine-1.0-video、grok-imagine-video-1.5-preview、grok-video-3

​
Seedance

  • 7 public models in total
  • doubao-seedance-1-0-lite-i2v-250428、doubao-seedance-1-0-lite-t2v-250428、doubao-seedance-1-0-pro-250528、doubao-seedance-1-0-pro-fast-251015、doubao-seedance-1-5-pro-251215、doubao-seedance-2-0-260128、doubao-seedance-2-0-fast-260128

​
Kling Images

  • 4 public models in total
  • kling-image、kling-omni-image、kolors-virtual-try-on-v1、kolors-virtual-try-on-v1-5

​
Kling Videos

  • 2 public models in total
  • kling-video、kling-*

​
Hailuo

  • 1 public model in total
  • hailuo*

​
Vidu

  • 2 public models in total
  • viduq3-turbo、vidu*