Docs / Overview

RelayDance Documentation

RelayDance is a video generation API. Submit a prompt to https://relaydance.com/v1/video/generations and receive a finished clip: Seedance 2.0 (480p, 720p, 1080p and native 4K, plus Fast and Mini), Seedance 1.5 Pro and HappyHorse models, up to 15 seconds, optional generated audio. Image generation with gpt-image-2 is included through the same OpenAI-compatible endpoint (image output is free, you pay only for input). RelayDance serves video and image only, no chat or LLM models.

Built for builders: tasks start immediately (no queue), no BytePlus account or KYC is required, face and portrait generation is supported, and you get access to special SKUs not available on the official platform. Failed requests are not billed.

Video tasks are asynchronous: submit, then poll, or set a webhook callback and never poll at all. One API key, one base URL, one balance. Get your API key and start building.

Quick Start

Submit a video task and poll it: two HTTP calls to a clip

Video Generation

Seedance 2.0, Seedance 1.5 Pro and HappyHorse via the async task API

Image Generation

gpt-image-2 images via /v1/images/generations

Upload Files

Upload reference media for image-to-video workflows

API Keys

Create and manage your API keys for authentication

API Reference

Endpoints, parameters and response formats

Why RelayDance?

✓Seedance 2.0 and HappyHorse: text-to-video and image-to-video up to 15s with audio, 480p to 4K
✓gpt-image-2 image generation with free image output, plus multi-reference fusion (9 images, 3 videos, 3 audio)
✓No queue, no KYC, face and portrait generation supported
✓Special SKUs beyond the official platform, pay with USDT or card, failed requests never billed

Quick Start→