Overview
doubao-seedance-2-0-260128 (standard) and doubao-seedance-2-0-fast-260128 (fast) are ByteDance’s latest video generation models, served through APIYI on official Volcengine Mainland China resources (not the BytePlus international edition) with upstream content-safety built in. They support text-to-video, first/first+last frame image-to-video, 1-9 reference images, and reference video/audio inputs — and can generate voice, sound effects, and background music synchronized with the visuals.🎬 Highlights: 4-15 s controllable duration (or
-1 for model-chosen length), three resolution tiers (480p/720p/1080p), 6 aspect ratios plus adaptive, synchronized audio on by default, and multilingual prompts (Chinese, English, Japanese, Spanish, Portuguese, Indonesian). Built for short-video production, e-commerce assets, motion design, and virtual-human content at scale.Video Generation API Reference
POST /seedance/api/v3/contents/generations/tasks — async task endpoint with an interactive Playground and full polling/download code.API Manual
Token creation, base URL, billing models, and general calling conventions.
Why APIYI’s Seedance 2.0?
Benchmarked against the Volcengine official channel, optimized for production workloads across stability, cost, and onboarding:Official Resource · Mainland Edition
Official Volcengine Mainland China resources (not BytePlus international), with upstream content safety built in. Parameters, responses, and billing match the official API exactly.
Unlimited Concurrency · No Queuing
In our tests, 15 simultaneous tasks all entered
running immediately with zero queuing (measured 2026-06-06 (UTC+8)) — ready for batch production at scale.Official Pricing + Top-up Bonuses
Unit prices aligned with Volcengine’s official list (on-platform billing runs roughly 10% higher); combined with top-up bonuses the effective cost is about on par with the official channel — without the CNY 200 activation deposit or enterprise verification.
Zero-friction Global Access
No Volcengine account or identity verification required. Mainland China data centers, residential networks, and overseas nodes can all reach
api.apiyi.com directly with a single Token.Professional Support
A team experienced in video-generation workloads, providing model selection, tuning, and integration support from PoC to production.
Key Features
Three Tiers · Same Price per Tier
480p / 720p / 1080p (1080p standard model only). Within a tier, 16:9, 9:16, 1:1, and every other ratio share the same pixel area and the same price — switch between landscape and portrait at zero cost.
Synchronized Audio by Default
generate_audio defaults to true: voice, sound effects, and background music are generated to match the visuals. Put spoken lines in double quotes to improve voice-over quality.4-15 s Controllable Duration
duration accepts whole seconds from 4 to 15, or -1 to let the model pick a length (billed by actual output). Fixed 24 fps.Multilingual Prompts
Chinese (up to ~500 chars) and English (up to ~1000 words), plus Japanese, Spanish, Portuguese, and Indonesian.
First / First+Last Frame
Animate a single image as the first frame, or pin both first and last frames with two images. Combine with
return_last_frame to chain clips into longer continuous videos.Multi-modal Reference
Mix 1-9 reference images with optional reference video and audio (the three image modes are mutually exclusive) to keep characters and style consistent.
Async Task Flow
Submit and get a
task_id, poll for status, then download the mp4 from content.video_url (link valid for 24 hours).Reproducible Seeds
Fix
seed for similar results across runs. watermark defaults to false — output is watermark-free.Pricing
Token-based billing:tokens ≈ duration(s) × width × height × 24 / 1024 (verified in our tests to within 0.1%). Since every ratio in a tier has the same pixel area, price depends only on the resolution tier and duration. Official public pricing (16:9 / 5 s / no input video):
| Resolution | Fast | Standard |
|---|---|---|
| 480p | CNY 1.86 | CNY 2.31 |
| 720p | CNY 4.00 | CNY 4.97 |
| 1080p | Not supported | CNY 12.39 |
| Resolution | Per 5 s | Per second | Per second (¥) | Best price | Best price (¥) |
|---|---|---|---|---|---|
| 480p | ≈$0.37 | $0.073/s | ¥0.51/s | $0.061/s | ¥0.43/s |
| 720p | ≈$0.79 | $0.157/s | ¥1.10/s | $0.131/s | ¥0.92/s |
| 1080p | ≈$1.77 | $0.354/s | ¥2.48/s | $0.295/s | ¥2.07/s |
Billing notes:
- Final charges follow the console’s model pricing and call logs. Due to tax, FX, and upstream settlement, on-platform billing may run roughly 10% above the official list; with top-up bonuses the effective cost is about on par with the official channel
- Tasks are pre-charged on submission and settled on completion — your balance fluctuates briefly; reconcile against call logs
- Rejected requests (HTTP 400 parameter errors, etc.) are not billed (verified)
- Cost scales linearly with duration: a 15 s video costs about 3× a 5 s one
- Fast and standard bill at the same rate on APIYI — choose fast for speed, standard for 1080p
Beta-supply notice: Seedance 2.0 is currently in a beta supply phase. If your actual charges deviate noticeably from the table above, contact customer support and we will reconcile. Pricing will be adjusted dynamically with upstream policy (e.g. if a lower-priced official variant ships later) and APIYI’s supply capacity; capable channel partners are welcome to reach out. This model is priced to secure supply and serve customers, not for profit.
Group Setup
Seedance 2.0 runs on the dedicatedSeeDance2 group (0.18x rate, CNY-denominated), with two hard requirements: ① the Token’s billing model must be Pay-as-you-go Priority (or Pay-as-you-go) — Pay-per-request tokens cannot route; ② the Token must have the SeeDance2 group enabled. Tokens on the Default group or other video groups will fail with “no available channel for this model”.
| Group | Rate | When to use |
|---|---|---|
SeeDance2 | 0.18x | The only group serving Seedance 2.0 — ample concurrency, no queuing |
| Setup | Best for | How |
|---|---|---|
| A. One shared Token | Personal projects, mixed model usage | Add SeeDance2 to your existing Token’s group list; keep billing model as Pay-as-you-go Priority |
| B. Dedicated Token | Production workloads, separate billing | Create a Token with only the SeeDance2 group — cleaner reporting, quota alerts per business line |
Technical Specs
| Dimension | Value |
|---|---|
| Models | doubao-seedance-2-0-260128 (standard) / doubao-seedance-2-0-fast-260128 (fast) |
| Resolutions | 480p / 720p / 1080p (no 1080p on fast) |
| Aspect ratios | 16:9 4:3 1:1 3:4 9:16 21:9 adaptive (default adaptive) |
| Duration | 4-15 whole seconds, or -1 model-chosen (default 5) |
| Frame rate | Fixed 24 fps (frames parameter not supported) |
| Audio | generate_audio defaults to true; mono |
| Input images | jpeg/png/webp/bmp/tiff/gif/heic/heif; aspect ratio (0.4, 2.5); sides (300, 6000) px; under 30 MB each |
| Input video/audio | Seedance 2.0 only; audio wav/mp3, 2-15 s per clip, up to 3 clips, must accompany an image or video |
| Generation time (measured) | 5 s @720p: ~2-5 min; 1080p: ~3 min; 15 s: ~4.5 min |
| Response fields | content.video_url (mp4 direct link, expires in 24 h), usage.completion_tokens |
| Task retention | task_id queryable for 7 days |
API Endpoints
| Endpoint | Purpose | Content-Type |
|---|---|---|
POST /seedance/api/v3/contents/generations/tasks | Create a video generation task | application/json |
GET /seedance/api/v3/contents/generations/tasks/{id} | Poll task status / fetch the video URL | — |
Resolutions & Aspect Ratios in Detail
A resolution tier defines the pixel area, not the short side. Actual output dimensions per ratio (official values, verified in our tests):| Ratio | 480p | 720p | 1080p (standard only) |
|---|---|---|---|
16:9 | 864×496 | 1280×720 | 1920×1080 |
4:3 | 752×560 | 1112×834 | 1664×1248 |
1:1 | 640×640 | 960×960 | 1440×1440 |
3:4 | 560×752 | 834×1112 | 1248×1664 |
9:16 | 496×864 | 720×1280 | 1080×1920 |
21:9 | 992×432 | 1470×630 | 2206×946 |
adaptive | Model picks one of the above based on the input | Same | Same |
How adaptive works
- Text-to-video: the model infers the best ratio from your prompt
- First / first+last frame: matches the first-frame image’s ratio (mismatched images are center-cropped)
- Multi-modal reference: follows prompt intent, otherwise the first media item (video takes priority over images)
- The actual ratio used is returned in the task response’s
ratiofield
Best Practices
Pick the model by output needs
Choose the standard model
doubao-seedance-2-0-260128 for 1080p or maximum quality; choose fast for batch production (same price on APIYI — its advantage is speed).Use adaptive to avoid cropping
For image-to-video keep the default
adaptive so the model matches your source image’s ratio. Lock 9:16 (portrait) or 16:9 (landscape) only when the target platform demands it.Duration is your cost dial
Cost scales linearly with length. Validate prompts with 5 s clips first, then scale to 10-15 s; use
duration: -1 when pacing is best left to the model.Turn audio off when you don't need it
generate_audio defaults to true. Pass false for silent footage you plan to score yourself.Quote dialogue for better voice-over
Put spoken lines inside double quotes in the prompt — the model generates matching voices automatically.
Add Accept-Encoding: identity in HTTP clients
The gateway labels responses
content-encoding: gzip while the body is uncompressed; auto-decompressing clients such as Python requests raise ContentDecodingError. Adding the Accept-Encoding: identity header avoids this (curl is unaffected).Poll every 15-30 s and download immediately
Tasks typically finish in 2-5 minutes.
content.video_url is a signed link valid for 24 hours — copy the file to your own storage as soon as the task succeeds.Error Codes & Retries
| Code | Meaning | Suggested handling |
|---|---|---|
400 | InvalidParameter: bad resolution/ratio/duration (e.g. fast + 1080p) | The message names the offending parameter — fix per the tables above; not billed |
401 | Invalid Token | Check the Bearer Token |
403 | Content moderation rejection (real faces, policy violations) | Change the assets or prompt |
429 | Rate limited / insufficient quota | Exponential backoff; check balance |
5xx | Gateway / backend error | Retry 1-2 times |
Task failed | Generation failed | Inspect the task’s error field; retry with a different seed if needed |
Task expired | Exceeded execution_expires_after (default 48 h) | Resubmit |
Client recommendations:
- 30-60 s request timeouts are enough for create/poll calls (the wait happens on the task side)
- Poll every 15-30 s with an overall budget of 15+ minutes (longer for 1080p / 15 s tasks)
- Apply exponential backoff on 5xx and timeouts (2 retries)
- Log the task
idand thex-request-idresponse header for troubleshooting
FAQ
I get 'no available channel for this model' — why?
I get 'no available channel for this model' — why?
The most common Seedance 2.0 error: your Token does not have the
SeeDance2 group enabled. Tokens on the Default group or other video groups cannot route to this model. Enable the SeeDance2 group in Token Settings and use the Pay-as-you-go Priority billing model.Python requests raises ContentDecodingError / gzip errors
Python requests raises ContentDecodingError / gzip errors
The gateway marks responses
content-encoding: gzip but the body is not compressed. Add "Accept-Encoding": "identity" to your request headers; curl and browser fetch are unaffected.Why does my video have sound? How do I turn it off?
Why does my video have sound? How do I turn it off?
generate_audio defaults to true (verified): the model adds voice, sound effects, and background music automatically. Pass "generate_audio": false explicitly for silent output.Where is the video URL, and why does it stop working?
Where is the video URL, and why does it stop working?
On success the URL is at
content.video_url in the poll response (not top-level). It is a signed link valid for ~24 hours — download and re-host it immediately. The task_id itself remains queryable for 7 days.What is the success status value?
What is the success status value?
The state machine is
queued → running → succeeded / failed / expired. The success state is succeeded, not completed — an easy mistake when migrating from other video APIs.Can I upload photos of real people for image-to-video?
Can I upload photos of real people for image-to-video?
No. Seedance 2.0 rejects reference images/videos containing real human faces (upstream content safety). Alternatives: reuse face-containing output generated by Seedance models within the last 30 days, use the platform’s preset virtual avatars (
asset:// IDs), or use licensed face assets.Am I billed for failed or rejected requests?
Am I billed for failed or rejected requests?
Parameter rejections (HTTP 400) are not billed (verified). Billing is pre-charged on submit and settled on completion, so your balance fluctuates briefly — reconcile against call logs.
How do I estimate token usage? Is portrait more expensive?
How do I estimate token usage? Is portrait more expensive?
tokens ≈ duration(s) × width × height × 24 / 1024, verified to within 0.1%. Every ratio in a tier has the same pixel area (720p 16:9 and 9:16 both cost 108,900 tokens per 5 s) — landscape, portrait, and square all cost the same.Fast vs standard — which one?
Fast vs standard — which one?
Both bill at the same rate on APIYI. Fast generates quicker but caps at 720p. Pick standard for 1080p or maximum detail; pick fast for high-volume 720p-and-below production.
What does duration: -1 do?
What does duration: -1 do?
The model picks a length between 4 and 15 s (our test produced a 10 s video) and bills by actual output. The final length is returned in the task’s
duration field. Fix the duration explicitly if cost predictability matters.Is the frames parameter supported for fractional seconds?
Is the frames parameter supported for fractional seconds?
No.
frames and camera_fixed are Seedance 1.x parameters — not supported by the Seedance 2.0 series. Use whole-second duration instead.Can I mix first-frame, first+last frame, and reference images?
Can I mix first-frame, first+last frame, and reference images?
No — they are three mutually exclusive modes: first frame (1 image), first+last (2 images with required
first_frame/last_frame roles), and multi-modal reference (1-9 images, all reference_image). To approximate “first/last frame + reference”, use reference mode and designate a frame via the prompt.Are there concurrency limits or queues?
Are there concurrency limits or queues?
The SeeDance2 group has ample concurrency with no queuing (15 simultaneous tasks all ran immediately in our test). Contact sales for larger sustained workloads.
Any prompt limitations?
Any prompt limitations?
Keep prompts under ~500 Chinese characters or ~1000 English words — longer prompts dilute detail. Supported languages: Chinese, English, Japanese, Spanish, Portuguese, Indonesian. Describe subject + action + camera movement + lighting/style.
Related Docs
- Video Generation API Reference & Playground -
POST /seedance/api/v3/contents/generations/tasks - Sora 2 Video Generation - OpenAI official-relay video channel
- VEO 3.1 Video Generation - Google official video channel
- Top-up Bonuses - effective cost about on par with the official channel
- API Manual - general calling conventions
Seedance 2.0 is one of the few first-tier 2026 video models that outputs synchronized audio by default. Combined with same-price aspect ratios and a 15-second ceiling, it is a strong primary channel for short-video and e-commerce asset production. To compare alternatives, the same Token (with extra groups enabled) can call Sora 2, VEO 3.1, and Wan2.7 directly.