RelayDanceDocs / Model APIs / Overview
Model APIs: Overview
All RelayDance requests share one base URL, https://relaydance.com/v1, and one API key. The model field in the request body selects which model handles it.
#Endpoints
| Modality | Endpoint |
|---|---|
Video (submit) | POST /v1/video/generations |
Video (poll) | GET /v1/video/generations/{task_id} |
Image | POST /v1/images/generations |
Chat | POST /v1/chat/completions |
File upload | POST /v1/files |
Model list | GET /v1/models |
#Listing available models
The authoritative model list is per key: call GET /v1/models with your key and you get exactly the IDs you can use. The public Models page shows the same catalog with pricing.
curl https://relaydance.com/v1/models \
-H "Authorization: Bearer YOUR_API_KEY"#Providers
Video, image and text models from leading AI labs:
| Provider |
|---|
ByteDance (Seedance) |
xAI (Grok) |
HappyHorse |
#Video models
| Model ID | Family | Notes |
|---|---|---|
| doubao-seedance-2-0-1080p | Seedance 2.0 | Flagship quality, 1080p output |
| doubao-seedance-2-0-720p | Seedance 2.0 | 720p output |
| doubao-seedance-2-0-fast-260128 | Seedance 2.0 | Faster generation |
| seedance-1-5-pro-with-audio | Seedance 1.5 | Generated audio included |
| seedance-1-5-pro-no-audio | Seedance 1.5 | Silent output |
| happyhorse-1.0-t2v | HappyHorse | Text-to-video |
| happyhorse-1.0-i2v | HappyHorse | Image-to-video |
| happyhorse-1.0-r2v | HappyHorse | Reference-to-video |
| happyhorse-1.0-video-edit | HappyHorse | Video editing |
| grok-imagine-video | Grok Imagine | xAI video generation |
| grok-imagine-video-1.5-preview | Grok Imagine | xAI 1.5 preview |
All video models use the asynchronous task API. See Video Generation.
#Image models
| Model ID | Family | Notes |
|---|---|---|
| grok-imagine-image | Grok Imagine | Fast image generation |
| grok-imagine-image-quality | Grok Imagine | Higher quality tier |
#Text models
Chat completions are served by the Grok family (for example grok-4.3) through the standard OpenAI-compatible endpoint. See LLM / Chat.
#Authentication
Every endpoint uses the same bearer token scheme:
| Header | Value |
|---|---|
Authorization | Bearer YOUR_API_KEY |
Content-Type | application/json |
#Synchronous vs asynchronous
Chat and image requests return their result in the response. Video generation is asynchronous: submitting returns a task_id, and you poll GET /v1/video/generations/{task_id} or receive a webhook via metadata.callback_url.