Skip to main content
ReachAPIReachAPI
Seedance 2.5

Seedance 2.5

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

Multimodal VideoUp to 30 SecondsAsync Tasks

Execution

Async video

Submit a task, then poll or use a callback

Duration

4-30s or auto

Use -1 for automatic duration selection

Resolution

480p / 720p

Seven fixed or adaptive aspect ratios

Token price

$6.40-$10.70 / 1M

Based on whether the input contains video

Model Codeseedance-2-5

Playground

seedance-2-5
First Frame0/1

Click or drag

Last Frame0/1

Click or drag

4s8s30s

Resolution (sent to backend)

Aspect Ratio (sent to backend)

No output yet

Pricing

Video inputResolutionToken price
No video input480p / 720p$10.70 / 1M output tokens
With video input480p / 720p$6.40 / 1M output tokens

Token rate · $11.77 · 1M tokens

Token rate · $7.04 · 1M tokens

README

Seedance 2.5 generates 4-30 second videos at 480p or 720p from text, image, video, audio, or audio-only input through ReachAPI's asynchronous task API.
  • Seedance 2.5 accepts text, images, videos, and audio, including audio-only input, for generation, editing, continuation, and reference-driven workflows.
  • It supports up to 30 images, 10 videos, and 10 audio files. Client media must use publicly reachable HTTPS URLs.
  • First/last-frame generation requires `aspect_ratio=adaptive` and cannot be mixed with reference media. Editing and extension use content plus prompt semantics rather than mode flags.

API

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

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

Model Code

seedance-2-5

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_R..._KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-5",
    "input": {
      "content": [
        {
          "type": "text",
          "text": "A cinematic train journey through a mountain valley at sunrise"
        }
      ],
      "duration_seconds": 12,
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "watermark": false
    }
  }'

Related Models

Related video models

MiniMax H3

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

Seedance 2

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

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.

Seedance 2.5 API