Does Seedance 2.5 support real-person reference images?

Yes. Seedance 2.5 on reAPI accepts real-person reference images and videos. Reference material passes an automated review before generation; anything rejected by moderation fails with a clear error and a full refund.

How does Seedance 2.5 pricing work?

Credit-based — 1 credit equals $0.001. The Seedance 2.5 cost scales with output duration × resolution × reference mode. Auto duration (duration -1) reserves at the 30-second cap and settles to the actual output length, refunding the difference.

Which Seedance 2.5 model id do I call?

One id covers everything: doubao-seedance-2.5-face. Text-to-video, image-to-video, first/last frame, and multimodal reference are selected implicitly by which fields you send — no separate variants to choose between.

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 30 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. You can also pass up to 10 reference audio tracks in audio_urls.

How long can a Seedance 2.5 video be?

Seedance 2.5 generates 4–30 seconds per request, or set duration to -1 and the model picks the best length. For even longer outputs, set return_last_frame and feed the URL into the next call to chain clips back to back without prompt drift.

Where is the full Seedance 2.5 reference?

The full Seedance 2.5 parameter list, task-type rules (video edits require duration -1), error codes, and runnable cURL examples live at /docs/seedance-2-5.

How do I choose between Seedance 2.5 and Seedance 2.0?

Pick Seedance 2.5 for longer clips (up to 30 s vs 15 s), bigger reference sets (30 images + 10 videos + 10 audios vs 9/3/3), audio-only reference, and prompt-driven video editing. Pick Seedance 2.0 when you need 4K output or the cheaper Fast and Mini tiers — 2.5 now serves up to 1080p.

Where can I use Seedance 2.5?

On reAPI, right on this page: run it in the playground above or call it through the async API on pay-as-you-go pricing. ByteDance also offers Seedance 2.5 in its own Dreamina app and through BytePlus ModelArk. For the Dreamina route, see https://reapi.ai/blog/dreamina-seedance-2-5-user-guide.

Is Seedance 2.5 free or paid?

Paid. Completed generations are charged at the rates in this page's pricing table. Eligible new accounts may receive promotional test credits; availability and amount are shown at signup or in the dashboard. Technical, provider, or moderation failures are refunded automatically.

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

Seedance 2.5 generates up to 30 seconds in a single pass, twice the length of Seedance 2.0, at 480p, 720p, or 1080p with synced audio. Each request takes up to 30 image, 10 video and 10 audio references.

Highlights: 4–30 s in one pass · 480p / 720p / 1080p · synced audio
Best for: Ads, UGC, talking-head clips, short drama
Input: Text, images, video or audio references
Output: Video with audio (mp4 / mov)

Input

Prompt

3–20000 chars

Duration (seconds)5

Auto — model picks the length

4–30 seconds

Aspect ratio

adaptive lets the model pick

Resolution

720p is the default

Bitrate Mode

Output video encoding bitrate. default: return the original video without processing. standard: compress for smaller files and faster downloads. high: lighter compression to preserve more detail than standard. Does not affect price.

Generate audio

on by default · mono

Output format

mp4 (default) or mov for pro color

Watermark

off by default

Return last frame

returns last_frame_url for chaining

Web search

wire shape: tools array with web_search type

Seed

same seed ≈ similar output

Content filter

wire field: content_filter (boolean) · default true · API only

Estimated cost~$1.3351,335 credits

Result

Try one of these prompts

Pricing

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

First test cost

$0.356356 credits

One 5-second sample at the cheapest tier.

Testing budget guide

Add credits

$10

≈ 28 tests

$50

≈ 140 tests

$100

≈ 281 tests

Category	Seedance 2.5 Real-person references allowed.	Seedance 2.5 Eco Economy tier. 720p / 1080p.
480P & uploaded videos	$0.072 Price · 1 second	—
480P	$0.119 Price · 1 second	—
720P & uploaded videos	$0.161 Price · 1 second	$0.121 Price · 1 second
720P	$0.267 Price · 1 second	$0.201 Price · 1 second
1080P & uploaded videos	$0.276 Price · 1 second	$0.207 Price · 1 second
1080P	$0.462 Price · 1 second	$0.347 Price · 1 second

What is the Seedance 2.5 API?

Seedance 2.5 is ByteDance's latest video generation model, exposed on reAPI as one async endpoint with five generation modes: text-to-video, image-to-video, first/last-frame, multimodal reference (up to 30 images, 10 videos, and 10 audio tracks — audio-only works too), and prompt-driven video editing with auto duration. Each request produces 4–30 seconds of video with synced speech, sound effects, and music, billed per second of actual output.

5 generation modes on one endpoint

Mode is implicit: which media fields you send decides how the request runs.

Text to video

prompt

Send a prompt alone and the model composes the shot from scratch.

Image to video

image_urls

Pass images in image_urls; the first becomes the opening frame.

First and last frame

image_with_roles

Give image_with_roles a start frame, optionally an end frame, and the model fills the motion between them.

Multimodal reference

image_urls + video_urls + audio_urls

Up to 30 images, 10 video clips and 10 audio tracks in one request. Audio-only input works too.

Prompt-driven editing

video_urls + duration: -1

Describe a change over a source clip. Editing tasks require duration -1 so the model keeps the source length.

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 and get a hero shot, pan, or push-in back in minutes. Set duration anywhere from 4 to 30 seconds, pick 480p for drafts and 720p or 1080p for the cut you ship, and iterate at the speed of prompts. No film crew, no storyboard, no edit timeline — and because billing is per second of actual output, an abandoned take costs seconds, not a shoot day.

Preview a clip

Bring stills to life as social videos

Pass a static image with a motion prompt and get a clip ready for Reels, Shorts, and TikTok. Choose 9:16, 1:1, or 16:9 up front so nothing needs re-cropping, let generate_audio score the clip, and chain shots with return_last_frame when one take is not long enough. Skip the storyboard, ship the post.

Animate real people from your own reference material

Reference images, video and audio can contain real people, and the model generates synced speech alongside the picture. One request takes up to 30 images, 10 clips and 10 audio tracks, so a character, a location and a voice can constrain the same shot. Audio-only input works too. You are responsible for holding the rights and consent for whatever you upload.

Why reAPI for Seedance 2.5

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.

How should you choose between Seedance 2.5, Seedance 2.0, and MiniMax H3?

Seedance 2.5 is not the automatic upgrade for every job. Compare with the same brief and inputs, then pick by clip length, resolution, and reference needs.

	Seedance 2.5	Seedance 2.0	MiniMax H3
Best suited to	16–30 s shots, large multimodal reference sets, real-person references, prompt-driven edits	Mature workflows, 4K delivery, cheaper Fast and Mini tiers	High-detail short clips with tight first/last-frame control
Duration	4–30 seconds, or -1 for model-chosen length	4–15 seconds	4–15 seconds (default 6)
Resolution	480p / 720p / 1080p	480p / 720p / 1080p / 4K	Fixed output (no resolution parameter)
Inputs	Text, first/last frames, up to 30 images + 10 videos + 10 audio tracks — audio-only works	Text, first/last frames, up to 9 images + 3 videos + 3 audios	Text, first/last frames, up to 9 images + 3 videos + 3 audios (audio needs image/video)
Cost decision	Per-second; measure cost per usable shot — longer single takes can replace edits and reruns	Keep your current baseline and A/B the same brief before upgrading	Reference-video seconds bill on top of output — compare with the same brief

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

docs/api/seedance-2-5

API reference

Drop-in code and the full parameter table.

View full reference

curl -X POST https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.5-face",
    "prompt": "A kitten yawning at the camera",
    "size": "16:9",
    "resolution": "720p",
    "duration": 5
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

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 live on reAPI — try it in the playground above or call it through the async API.