Skip to main content
ByteDance SeedAug 7, 2026

Seedance 2.5

seedance-2-5-text-to-video-basicAnonymized

Seedance 2.5 is the next generation of ByteDance Seed’s cinematic video model, with native audio and stories of up to 30 seconds. This text-to-video variant generates 4- to 30-second clips at up to 4K.

from$0.1343
per second of video
4K
max resolution, 4 sizes
30s
longest clip, from 4s
Mode

Same prompt, other models

Every video model renders the same reference prompts, so their clips line up side by side. Hover a clip to play it.

Slow aerial drone shot gliding over a misty mountain valley at golden hour, sunlight piercing clouds onto a winding river, ancient pine forests on either side, ultra-smooth motion, professional color grading, atmospheric haze, 4K

Pricing

Billed per clip in USD, by length and resolution. Each resolution is drawn to scale.

Price per clip by length and resolution, with audio
480p720p1080p4K
Per second$0.1343$0.2903$0.7153$1.14
4s clip$0.54$1.16$2.86$4.57
5s clip$0.67$1.45$3.58$5.71
10s clip$1.34$2.90$7.15$11.42
30s clip$4.03$8.71$21.46$34.26

Audio on or off costs the same. Quoted from POST /video/quote on Nov 16, 2026. Prices can change, so quote a job before you queue it.

Estimate a batch

Resolution
Length5s
Audio
$1.45per 5s clip
$14.50for 10 clips

Against other video models

How it comparesamong 59 video models
Price per secondcheaper than 22%$0.1343
Longest cliplonger than 86%30s

Further right is better. Hover a dot for its model.

Capabilities

4 modes, each with its own model ID.

Text to videoseedance-2-5-text-to-video-basic
Takes prompt
Image to videoseedance-2-5-image-to-video-basic
Takes prompt and image
Reference to videoseedance-2-5-reference-to-video-basic
Takes prompt, reference images and audio
Video editseedance-2-5-edit-video-basic
Takes prompt, video and audio
Audioaudio: true | false

Aspect ratios

21:916:94:31:13:49:16

Specs

Model ID
seedance-2-5-text-to-video-basic
Mode
Text to video
Endpoint
POST /api/v1/video/queue
Resolutions
480p, 720p, 1080p, 4K
Lengths
4–30s, any whole second
Aspect ratios
21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Audio
Optional, on by default
Inputs
Prompt
Prompt limit
15,000 characters
Privacy
Anonymized
Weights
Closed
Added
Aug 7, 2026

Other versions

  1. Seedance 2.0Mar 2026
  2. Seedance 2.5Aug 2026

Quickstart

Video is asynchronous: queue a job, then poll for the clip.

  1. 1QuotePOST /video/quoteOptional. Prices the job in USD without charging for it.
  2. 2QueuePOST /video/queueChecks and charges the job, then returns a queue_id at once.
  3. 3RetrievePOST /video/retrievePoll it with the queue_id until the video is ready.
# 1. Queue the job (returns a queue_id)
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5-text-to-video-basic",
"prompt": "Slow aerial drone shot over a misty mountain valley at golden hour",
"duration": "5s",
"resolution": "720p",
"aspect_ratio": "21:9",
"audio": true
}'

# 2. Poll until the MP4 is ready (JSON with the status until then)
curl https://api.venice.ai/api/v1/video/retrieve \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "seedance-2-5-text-to-video-basic", "queue_id": "<queue_id>" }' --output video.mp4

# If the queue response has a download_url, retrieve only reports the
# status: download the MP4 from that URL once it is COMPLETED.
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelseedance-2-5-text-to-video-basicRequired
promptUp to 15,000 charactersRequired
duration4–30s, any whole secondRequired
resolution480p | 720p | 1080p | 4kOptional
aspect_ratio21:9 | 16:9 | 4:3 | 1:1 | 3:4 | 9:16Required
audiotrue | falseDefault true