Seedance 2

ByteDance's Seedance 2 video model for multimodal reference input, editing, extension, and asynchronous generation.

Multimodal VideoEditing + ExtensionAsync Tasks

Execution

Async video

Built for queued generation workflows

Duration

4-15s

Output length range for generated clips

Reference Types

Text / image / video / audio

Video input uses separate token rates

Token Price

$4.30-$7.70 / 1M

Varies by resolution and video input

Model Codeseedance-2

Playground

Model Code

seedance-2

Reference inputs

First Frame0/1

Click or drag

Last Frame0/1

Click or drag

Enter your prompt here...

Resolution

4s8s15s

Resolution

Resolution (sent to backend)

Aspect Ratio

Aspect Ratio (sent to backend)

Output

No output yet

Pricing

Video input	Resolution	Token price
No video input	480p / 720p	$7.00 / 1M tokens
No video input	1080p	$7.70 / 1M tokens
With video input	480p / 720p	$4.30 / 1M tokens
With video input	1080p	$4.70 / 1M tokens

Token rate · $7.35 · 1M tokens

Token rate · $4.515 · 1M tokens

Token rate · $8.085 · 1M tokens

Token rate · $4.935 · 1M tokens

Token rate · $4.2 · 1M tokens

Token rate · $2.52 · 1M tokens

Example 5s video · $0.3675 · video

Example 5s video · $0.798 · video

Example 5s video · $1.9635 · video

Example 5s video · $4.0845 · video

README

Seedance 2 is the full Seedance 2 video model on ReachAPI, supporting text, image, video, and audio reference workflows with 4-15 second outputs and token pricing by resolution and video input.

Seedance 2 supports multimodal creative workflows with text prompts and image, video, or audio references.
It is designed for advanced video generation, editing, continuation, and reference-driven motion work.
Use this model for the full Seedance 2 capability set, including reference video workflows, editing, extension, and 1080p output.

API

Use the API docs for request format, parameters, and integration details.

ByteDance's Seedance 2 video model for multimodal reference input, editing, extension, and asynchronous generation.

Model Code

seedance-2

View API Docs

API

Endpoint

POST /v1/vids/create

Authentication

Authorization: Bearer YOUR_REACH_API_KEY
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1/vids/create" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2",
    "input": {
      "content": [
        {
          "type": "text",
          "text": "A stylized travel film scene with dynamic camera movement"
        }
      ],
      "duration_seconds": 8,
      "resolution": "1080p",
      "aspect_ratio": "adaptive",
      "watermark": false
    }
  }'

Related Models

MiniMax H3

MiniMax Hailuo-03 for high-quality asynchronous video generation with frame and multimodal references.

Seedance 2.5

ByteDance's Seedance 2.5 model for long-form multimodal video generation, editing, extension, and audio-driven creation.

Seedance 2 Fast

ByteDance's faster Seedance 2 variant for multimodal asynchronous video generation at lower per-second rates.

Seedance 1.5 Pro

ByteDance's Seedance 1.5 Pro video model for higher-capability text and frame-guided video generation.

Seedance 1.0 Pro

ByteDance's Seedance 1.0 Pro video generation model for text-guided and frame-guided cinematic video tasks.

Seedance 1.0 Pro Fast

ByteDance's faster Seedance 1.0 Pro variant for lower-cost asynchronous video generation.