バリアント · Bytedance / Seedance

Seedance seedance-2.0 API

A model variant exposed through RunAPI's unified AI API.

Operational · video · Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/seedance -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the Seedance skill for me:

1. Clone https://github.com/runapi-ai/seedance
2. Copy the skills/seedance/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
Switch variant
概要

Seedance seedance-2.0 is available through the same RunAPI auth, SDKs, and agent skill workflow.

  • Unified endpoint
  • SDK snippets
  • Agent install path
  • 失敗した生成は課金されません
料金

料金

失敗した生成は課金されません
Text to video
$0.41 / second
仕様

仕様

Model ID seedance-2.0
プロバイダー Bytedance
モダリティ video
Task type asynchronous
課金 second
Endpoint /api/v1/seedance/text_to_video
Commercial Yes
Status Operational
クイックスタート

Quickstart — seedance-2.0

runapi.ai
curl -X POST https://runapi.ai/api/v1/seedance/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance-2.0",
  "prompt": "Generate a 10-second product reveal video: a smartphone emerges from smoke with cinematic lighting and ambient bass."
}'
import { SeedanceClient } from "@runapi.ai/seedance";

const client = new SeedanceClient();
const result = await client.textToVideo.run({
    model: "seedance-2.0",
    prompt: "Generate a 10-second product reveal video: a smartphone emerges from smoke with cinematic lighting and ambient bass.",
});
require "runapi/seedance"

client = RunApi::Seedance::Client.new
result = client.text_to_video.run(
    model: "seedance-2.0",
    prompt: "Generate a 10-second product reveal video: a smartphone emerges from smoke with cinematic lighting and ambient bass."
)
@runapi.ai/seedance v1
仕組み

How to use seedance-2.0

01

Choose endpoint

Pick the endpoint and copy the SDK snippet.

02

Pass model ID

Use this variant ID in the request body.

03

Run task

Submit the request and store the returned task ID.

04

Collect output

Poll or receive the callback when the task finishes.

違い

How seedance-2.0 compares

VS SEEDANCE-1.5-PRO

Up to 9 ref images + 3 video + 3 audio; 15-sec multi-shot

First audio+video in one pass; lip-sync, multilingual dialogue

VS SEEDANCE-2.0-FAST

Up to 9 ref images + 3 video + 3 audio; 15-sec multi-shot

Same 2.0 capabilities, 36% cheaper, slightly lower motion fidelity

VS SEEDANCE-V1-LITE

Up to 9 ref images + 3 video + 3 audio; 15-sec multi-shot

720p budget tier; optimized for social media

ユースケース

Where to use this variant

Product video

Generate short production-ready clips from prompts.

Creative iteration

Test multiple directions quickly.

Agent workflows

Let agents create video assets via tool calls.

FAQ

Frequently asked questions about seedance-2.0

How do I select seedance-2.0?

Pass the model ID shown in the quickstart.

Is pricing usage-based?

Yes. Pricing is metered per call or unit.

今すぐ開始

Start with Seedance today.