APIPod logoAPIPod

Official full-capability at 5% off · Seedance 2.5

Seedance 2.5: 30-second storytelling, audio and picture generated together

ByteDance's next-generation audio-video joint generation model — built for 30-second narratives with precise reference control.

Seedance 2.5 doubles the single-clip ceiling to 4–30 seconds and raises the multimodal reference budget to 30 images, 10 videos and 10 audios per request. On APIPod you call the official full-capability model at 5% off list price through one unified API — discount, special-offer and X ultra-low-price routes share the same endpoint, and public URLs on the discount and special-offer routes are reviewed for you automatically.

Max duration

30s per clip

4–30s per generation; extend for longer cuts

Native audio

Audio + video

Dialogue, ambience and music synced to the frame

Reference budget

30 / 10 / 10

Up to 30 images, 10 videos, 10 audios per request

API routes

8 models

t2v / i2v / r2v × discount / special-offer, plus X ultra-low-price t2v / i2v / r2v

Seedance 2.5 vs 2.0 — what changed?

Same Seedance DNA; twice the runtime and a much larger reference budget.

Move to Seedance 2.5 when…

  • The story needs more than 15 seconds — vlogs, ads, dialogue scenes and one-take action up to 30s
  • Consistency demands a full reference pack: character sheets, locations, motion clips and voice tracks in one request
  • You want native audio — spoken lines, ambience and music generated with the picture
  • You need the official full-capability model at the lowest per-token cost available

Stay on Seedance 2.0 when…

  • Final delivery needs 4K ultra HD — the 2.5 discount tier tops out at 1080P; use the 2.0 standard tier for 4K (now live on APIPod)
  • You rely on the fast / mini / lite tiers for specialized speed or cost profiles
  • Existing 2.0 prompts already produce the shots you need at 5–15s

Spec comparison at a glance

Seedance 2.5 extends the 2.0 contract instead of replacing it — the model field is the only change most integrations need.

SpecSeedance 2.5Seedance 2.0
Duration per clip4–30s (default 4s)4–15s (default 5s)
Resolution tiersDiscount / X ultra-low-price: 480P / 720P / 1080P; special-offer: 480P generation, AI-upscaled 720PUp to 4K
Reference imagesUp to 30Up to 9
Reference videosUp to 10Up to 3
Reference audiosUp to 10Up to 3
Native audioYes — on by defaultYes

Both generations ship through APIPod's full-capability pipeline: media URLs are reviewed by the asset service before submission, so plain public URLs work in requests. Billing is token-based on successful tasks only — see the pricing page for live rates.

Discount, special-offer, or X ultra-low-price?

All three share one endpoint — switching is a single model field. The special-offer tier natively generates at 480P via the official model and upscales to 720P with APIPod's in-house AI super-resolution (best for close-ups; wide shots prefer the discount tier's native rendering). X ultra-low-price is the cheapest route in the 2.5 family, at the cost of first-frame-only image-to-video and lower stability.

CriteriaDiscountSpecial-offerX Ultra-Low-Price
Model IDsseedance-2.5-t2v / i2v / r2vseedance-2.5-lite-t2v / i2v / r2vseedance-2.5-x-t2v / i2v / r2v
Resolution480P / 720P / 1080P480P generation, AI-upscaled 720P480P / 720P / 1080P
Clip length4–30s4–30s4–30s (default 5s)
ModesText / image / reference, plus dedicated edit, extend and draft modelsText / image / referenceText / first-frame image / reference (no last frame)
Reference limits30 images / 10 videos / 10 audios30 images / 10 videos / 10 audios30 images / 10 videos / 10 audios (audio needs an image or video)
Audio & advanced paramsNative synced audio, generate_audio on by defaultNative synced audio, generate_audio on by defaultNo generate_audio / seed / watermark parameters
Billing5% off official list price, per tokenSpecial-offer pricingPer second, lowest in the family; with reference video, reference + output length are billed together
StabilityHighest (official channel)High (official model at 480P + platform AI upscaling)Below official — longer peak queues and higher failure rates, use retries
Best for1080P delivery and distant / wide scenes, edit / extend / draft workflowsClose-up-driven batch delivery of full-capability 720P clipsBudget-sensitive batch trials, demos, and other retry-tolerant work

X ultra-low-price runs on an unofficial low-cost channel: public URLs are passed straight through without asset review, and assetId:// library references are not supported. Live per-edition prices are on the pricing page.

Official list price · 5% off

Official pricing reference

Seedance 2.5 bills by tokens on the official side: token consumption per second scales with resolution, and a video reference is billed for the reference duration together with the output duration at a lower unit price.

ResolutionTokens per secondWithout video referenceWith video reference
480P9,607.5 tokens/s$10.7 /M tokens · ≈ $0.103/s$6.4 /M tokens · ≈ $0.062/s
720P21,600 tokens/s$10.7 /M tokens · ≈ $0.231/s$6.4 /M tokens · ≈ $0.138/s
1080P≈ 38,500 tokens/s$10.7 /M tokens · ≈ $0.412/s$6.4 /M tokens · ≈ $0.246/s

With-video billing counts reference-video duration plus output duration as tokens. Official example — 10s reference + 10s output: 480P $1.23, 720P $2.76 per clip.

List prices from the official Seedance 2.5 pricing page; APIPod's discount tier bills at 5% off. The special-offer routes (seedance-2.5-lite-*) upscale a natively generated 480P clip to 720P with APIPod's in-house AI — 1080P is not available there. Your actual rates on APIPod are shown on the pricing page.

What Seedance 2.5 is built for

Longer narratives, better control — the official positioning, delivered through one API.

30-second one-take stories

Write the clip as timed beats — setup, action, payoff — and Seedance 2.5 holds blocking, wardrobe and scene logic across the full take. Extend twice for even longer cuts.

Reference-driven consistency

Up to 30 images, 10 videos and 10 audios per request: character identity, product appearance, motion paths and voice tracks each get an explicit job in the prompt.

Audio-video joint generation

Dialogue, ambience and music are generated together with the visuals and land on the frame — including invented-language performances and perfectly timed SFX.

Professional camera language

Orbits, whip pans, speed ramps, handheld tracking and invisible-cut staging: name the move and the model executes it with cinematic framing.

Video editing, prompt-driven

Swap backgrounds, restyle scenes or remove elements from an existing clip — the output keeps the source timeline and ratio. Fix the intent up front and constraints fail fast at submission, not minutes later.

View docs

Seamless video extension

Prolong an existing clip forward or backward with coherent motion and audio — chain into multi-shot narratives beyond the 30-second single-take limit.

View docs

Draft first, then a 1080P final

seedance-2.5-draft renders a low-cost 480P preview first. When it completes, send its task_id back as draft_task_id — just the model, draft_task_id and output format — and the 1080P final reuses the exact prompt, media, duration and seed. No re-roll, no surprise; one draft can spawn multiple finals.

View docs

Recommended workflow: draft wide, finalize once

1) Draft at 480P

Run seedance-2.5-draft to validate composition, timing and reference roles cheaply — and test a 5–10s opening before committing to the full 30s.

2) Borrow proven prompts

Start from the community templates in the prompt library; each detail page explains the beat structure so you can rebuild the rhythm for your subject.

3) Finalize at 1080P from the draft

Pass the winning draft's task ID as draft_task_id: the 1080P final reuses the same prompt, references, duration and seed, so what you approved is what you get. Need 720P? Rerun the prompt on the t2v / i2v / r2v routes; fix a single failed beat by editing only that time range.

4) One API, every Seedance

Switch between 2.5 and 2.0 tiers by changing the model field — auth, billing and observability carry over.

Example request

Seedance 2.5 quick start

Public model IDs on one endpoint: discount routes seedance-2.5-t2v for text-to-video, seedance-2.5-i2v for first/last-frame animation and seedance-2.5-r2v for multimodal references; special-offer seedance-2.5-lite-* routes bill at special-offer rates (native 480P generation + AI upscaling to 720P). Two-stage seedance-2.5-draft renders a 480P draft first, then a 1080P final from draft_task_id.

Media URLs are reviewed by the asset service automatically — pass plain public URLs and the pipeline exchanges them for approved asset references. Tasks are asynchronous; poll the task ID until completed.

curl -X POST https://api.apipod.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d {
    "model": "seedance-2.5-t2v",
    "prompt": "A cinematic tracking shot through a rain-soaked neon street, realistic motion, synchronized ambient sound.",
    "duration": 8,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }

Seedance 2.5 FAQ

What is Seedance 2.5?

Seedance 2.5 is ByteDance's next-generation audio-video joint generation model, built for 30-second storytelling. It generates video with synchronized native audio, follows timed-beat prompts, and accepts large multimodal reference packs for identity, motion and voice control.

How long can a Seedance 2.5 video be?

A single generation runs 4–30 seconds (default 4s). For longer narratives, write the clip as timed beats and extend the result — the official guidance allows extending twice for longer cuts.

What is the difference between Seedance 2.5 and 2.0?

2.5 doubles the per-clip ceiling from 15s to 30s and raises reference limits from 9 images / 3 videos / 3 audios to 30 / 10 / 10. On resolution, the discount routes output 480P / 720P / 1080P natively and the special-offer routes (seedance-2.5-lite-*) upscale a native 480P clip to 720P with AI, while Seedance 2.0 supports up to 4K. Prompt structure, native audio and the asset-review pipeline are shared.

Does Seedance 2.5 support 1080P or 4K?

Yes for 1080P. The discount routes (seedance-2.5-t2v / i2v / r2v) output native 480P / 720P / 1080P; the special-offer routes (seedance-2.5-lite-*) upscale a native 480P clip to 720P — not native 720P rendering. For 4K masters, use the Seedance 2.0 standard tier (4K now live on APIPod).

What is Seedance 2.5 X ultra-low-price, and how does it differ from the special-offer edition?

X ultra-low-price (seedance-2.5-x-t2v / seedance-2.5-x-i2v / seedance-2.5-x-r2v) is the cheapest route in the Seedance 2.5 family, running on an unofficial low-cost channel with per-second billing. It supports 480P / 720P / 1080P, 4–30 second clips and a 30 image / 10 video / 10 audio reference budget; image-to-video takes a single first-frame image (no last frame), the generate_audio / seed / watermark parameters are not supported, and stability is below the discount and special-offer editions (longer peak queues, higher failure rates). With reference video, its length is billed together with the output length. Use it for budget-sensitive, retry-tolerant batch work; for critical delivery stick with the discount or special-offer edition.

Does Seedance 2.5 generate audio?

Yes. Audio-video joint generation is on by default (generate_audio=true): dialogue, ambience and music are produced together with the visuals. You can disable it per request, and steer voices and sound with reference audio clips on the r2v route.

How do I call Seedance 2.5 through the API?

POST to /v1/videos/generations with model set to seedance-2.5-t2v, seedance-2.5-i2v or seedance-2.5-r2v. The task is asynchronous — poll the returned task ID until status is completed. Media URLs you pass are reviewed by the asset service automatically, so plain public URLs just work.

Can Seedance 2.5 edit or extend an existing video?

Yes — via the dedicated seedance-2.5-edit and seedance-2.5-extend models. Both pin the omni-reference sub-task type so parameter constraints are validated at submission time instead of failing asynchronously. Editing output follows the source video (duration and ratio not settable); extension output is 4-30 seconds. Both accept @视频N / @图N tokens in the prompt to address materials explicitly.

How does the Seedance 2.5 draft workflow work?

Four steps with the same model, seedance-2.5-draft. 1) Submit a normal request at 480p to get a draft, billed at the 480p rate. 2) Poll GET /v1/videos/status/{task_id} until status is completed — that task's data.task_id is your draft_task_id. 3) Submit only model and draft_task_id, plus optional resolution (1080p) and output_format; the prompt, media, duration, aspect ratio, seed and audio setting are reused, and resending them returns an error. 4) Poll the new task for the 1080p final, billed at the 1080p rate for the draft duration. Drafts stay valid for 7 days and both stages run on the same generation account.

Tell 30-second stories with Seedance 2.5

Official full-capability model at 5% off, deeper special-offer pricing, one unified API — your first clip is one request away.