Docs

Seedance 2.0 Fast API developer guide

Seedance 2.0 Fast is currently "Available". This guide provides model IDs, price snapshots, and copyable examples for integration. Seedance 2.0 Fast model page

Overview

Vendor: ByteDance
Type: Video
Number of tiers: 1
Endpoint tags: video-task

Available tiers and pricing

The model in requests must use the model IDs in the table below, case-sensitive.

Tier	Model ID	Input	Output	Context
Seedance 2.0 Fast	`seedance-2.0-fast`	$0.062700–$0.158400 / 秒	总价由输出时长、参考媒体时长和所选档位共同计算	—

Prices are build-time snapshots; refer to the pricing page and console for the latest prices.

Base URL and authentication

Base URL is https://api.rokoapi.com/v1. All requests must include Authorization: Bearer $OPENAI_API_KEY.

Console

Quickstart

curl https://api.rokoapi.com/v1/videos/tasks \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance-2.0-fast",
  "prompt": "A cinematic product shot with natural camera movement",
  "generation_type": "text",
  "duration": 5,
  "quality": "720p",
  "aspect_ratio": "adaptive"
}'

Common parameters

Parameter	Description
`model`	Use the public model IDs from the table above.
`prompt` / `messages`	Input prompt, conversation messages, or generation instructions; format depends on the endpoint.
`quality` / `duration` / `image_urls`	Generation models can accept size, quality, duration, aspect ratio, or reference asset URLs based on model capabilities.

After a successful async generation task submission, a task ID is returned. Poll GET /v1/tasks/{task_id} until the status becomes completed or failed.

Notes

Use only the model IDs listed on this page; unprovisioned or retired names will return a model unavailable error.
If you encounter a 403 error, check your account balance, key group, and model access permissions.
Multimodal, tool calling, caching, and streaming capabilities depend on the upstream model and channel configuration; refer to actual responses.