When will Seedance 2.5 be available?

Seedance 2.5 is coming soon. The playground and pricing on this page are a preview seeded from the current Seedance generation; the live API, final parameters, and rates will be published when it ships.

How will Seedance 2.5 pricing work?

Credit-based — 1 credit equals $0.001. The Seedance 2.5 cost will scale with output duration × resolution × reference mode, the same dimensions as the current Seedance family. Final rates are confirmed at launch.

Which Seedance 2.5 variant should I pick?

Standard for general use. Fast variants for cheaper, lower-resolution drafts. Face variants when you upload real-person references. Fast-face combines both acceleration tricks. All four share one request shape.

Can Seedance 2.5 animate a still image?

Yes. Pass image URLs in image_urls and Seedance 2.5 switches to image-to-video. The first image becomes the first frame; the prompt drives the motion. Up to nine reference images per request.

Does Seedance 2.5 generate audio?

Yes. Set generate_audio to true and Seedance 2.5 synthesizes an audio track that plays with the video. Pass audio_urls to drive lip-sync on the Seedance 2.5 face and fast-face variants.

Where is the full Seedance 2.5 reference?

The Seedance 2.5 parameter list, error codes, and runnable cURL examples will live at /docs/seedance-2-5 when the model launches.

Seedance 2.5 — Text, Photo, Video & Audio to Video

Q: How long can a Seedance 2.5 video be?

Each generation is a few seconds. For longer outputs, set return_last_frame and feed the URL into the next call to chain Seedance 2.5 clips back to back without prompt drift.

Seedance 2.5 is ByteDance's next-generation video model — turn text, photos, clips, or audio into short video. Coming soon to reApi with per-second pricing and an async OpenAI-style endpoint.

Input

Prompt*

3–20000 chars

Duration (seconds)5

4–30 seconds

Aspect ratio

adaptive lets the model pick

Resolution

720p is the default

Generate audio

on by default · mono

Output format

mp4 (default) or mov for pro color

Return last frame

returns last_frame_url for chaining

Web search

wire shape: tools array with web_search type

Estimated cost1,335 credits≈ $1.335

Result

Try one of these prompts

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Spin up product demos with Seedance 2.5

Send one product photo to Seedance 2.5 and get a hero shot, pan, or zoom video back in minutes. Iterate on cuts at the speed of prompts — no film crew, no storyboard, no edit timeline.

Preview a clip

Bring stills to life as social videos

Pass a static image with a motion prompt. Seedance 2.5 returns a short clip ready for Reels, Shorts, and TikTok. Skip the storyboard, ship the post.

Lip-sync real people with the Face variants

Combine reference video and audio with the Seedance 2.5 face variants to animate real people speaking. One call covers voiceovers, explainers, and character animation.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

Model	Category	Price
doubao-seedance-2.5-face	480P & uploaded videos	$0.072 72 credits · 1 second
	480P	$0.119 119 credits · 1 second
	720P & uploaded videos	$0.161 161 credits · 1 second
	720P	$0.267 267 credits · 1 second

Why reAPI

Next-generation quality

Seedance 2.5 builds on the Seedance family with sharper motion, stronger prompt adherence, and richer multi-modal control — text, image, video, and audio in one shape.

Per-second credit pricing

1 credit equals $0.001. The Seedance 2.5 cost scales with seconds × resolution × reference mode. Failed jobs are refunded automatically — you only pay for video that ships.

Async with continuous chaining

Submit returns a task ID instantly. Set return_last_frame and feed the URL into the next call to chain unlimited Seedance 2.5 video without re-prompting.

Seedance 2.5 vs Veo 3

How ByteDance's Seedance 2.5 is positioned against Google's Veo 3 for short-form video generation.

Capability

Seedance 2.5

Veo 3

Input modes

Text, image, first/last frame, reference video, and reference audio

Text and image to video

Audio

Optional generated audio plus reference-audio lip-sync

Native synchronized audio

Real-person inputs

Supported via the Face variants

Restricted

Pricing model

Per-second credits, refunded on failure

Per-second, premium tier

Variants

Standard, fast, face, and fast-face share one request shape

Single flagship tier

API access

Async OpenAI-style endpoint on reApi (coming soon)

Available through Google tooling

Comparison reflects publicly documented behavior at the time of writing and may change. Seedance 2.5 details on this page are a preview and will be finalized at launch.

Integrate Seedance 2.5 in three steps

step 01
Create an API key
Sign up and grab a key from the dashboard. Free credits will cover your first Seedance 2.5 generations — no card required.
Open
step 02
Submit a video task
POST your prompt to /api/v1/videos/generations with the model field set to a Seedance 2.5 variant. The endpoint returns a task ID immediately.
Open
step 03
Poll the result
GET /api/v1/tasks/:id until status is completed. Download the Seedance 2.5 output video and ship it.
Open

Frequently asked questions

Common questions about this model.

Seedance 2.5 is the next-generation video model in ByteDance's Seedance family. It turns text, images, video, and audio into short video clips. Seedance 2.5 is coming soon on reApi — this page is a preview.