bytedance logo
bytedance

ByteDance: Seedance 1.5 Pro

Source description (English)

ByteDance's next-generation audio-visual generation model with a 4.5B parameter Dual-Branch Diffusion Transformer architecture. Seedance 1.5 Pro generates video and audio simultaneously in a single unified pass — eliminating the timing...

Overview

Model specifications

Context
Not provided
Maximum output
Not provided
Architecture
text+image->video
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Video (with audio)
$0.0518
per second
  • 480p$0.0231
  • 720p$0.0518
  • 1080p$0.1166
  • 4K$0.4666
Video (no audio)
$0.0259
per second
  • 480p$0.0115
  • 720p$0.0259
  • 1080p$0.0583
  • 4K$0.2333
Video Tokens (with audio)
$2.4
per 1M tokens
Video Tokens (no audio)
$1.2
per 1M tokens
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

This creates a video job. Poll its status before downloading the completed video.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/videos \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"bytedance/seedance-1-5-pro","prompt":"A slow camera move across a sunlit mountain landscape"}'

# Replace JOB_ID with the returned id to check progress.
curl --fail-with-body "https://openrouter.ai/api/v1/videos/JOB_ID" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY"
Capabilities

InputOutput

Input
textimage
Output
video
API

Supported API parameters

frequency_penalty
Available providers

1 Provider

Checked: September 22, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Seed

Not provided
Context
Not provided
Maximum output
Not provided
bytedance

4 models

All models
bytedance logobytedance

ByteDance: Seedance 2.0 Mini

Seedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It...

Context
Not provided
Input
text · image · video · audio
Output
video
Video (with audio): $0.0302 per secondVideo (no audio): $0.0302 per second
View model details
bytedance logobytedance

ByteDance: Seedance 2.5

Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up...

Context
Not provided
Input
text · image · video · audio
Output
video
Video (with audio): $0.2311 per secondVideo (no audio): $0.2311 per second
View model details
bytedance logobytedance

ByteDance: Seedance 2.0

Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency,...

Context
Not provided
Input
text · image · video · audio
Output
video
Video (with audio): $0.1512 per secondVideo (no audio): $0.1512 per second
View model details
bytedance logobytedance

ByteDance: Seedance 2.0 Fast

Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost...

Context
Not provided
Input
text · image · video · audio
Output
video
Video (with audio): $0.0907 per secondVideo (no audio): $0.0907 per second
View model details