Skip to content
Model infoModelsSnapshot: 15 Oct 2026

ByteDance / Seedance

Seedance 1.0 Pro Fast (251015)

Seedance 1.0 Pro Fast video-generation revision 251015, supporting text and reference-image inputs.

Video generation
availableClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
8 of 22 specification fields collected
Output resolution480p, 720p, 1080pSee specification notes below
Clip duration2–12 sSee specification notes below
Input billingSee ratesBytePlus ModelArk
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
VideoSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected
Output resolutions
480p, 720p, 1080pSource for Output resolutions (opens in a new tab)
Video duration
2–12 sSource for Video duration (opens in a new tab)
Frame rate
24 fpsSource for Frame rate (opens in a new tab)
Output formats
.mp4Source for Output formats (opens in a new tab)
Flex inference
SupportedSource for Flex inference (opens in a new tab)
Published request quota
* default: * Max RPM: 600 * Max concurrency: 10 * flex: * TPD: 500BSource for Published request quota (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

BytePlus ModelArk · standard

Provider source (opens in a new tab)
API model ID
seedance-1-0-pro-fast-251015
Access
ModelArk API access requires an eligible BytePlus account and enabled model. Published quotas are account-dependent.
Regions
Not collected
Service tier
standardSource for Service tier (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Video generationOutput1$1.001M video tokens

Rate conditions

  1. Online generation. Only successful video outputs billed. Actual completion_tokens determines charges; duration, frame rate and resolution affect usage.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

BytePlus ModelArk · flex

Provider source (opens in a new tab)
API model ID
seedance-1-0-pro-fast-251015
Access
ModelArk API access requires an eligible BytePlus account and enabled model. Published quotas are account-dependent.
Regions
Not collected
Service tier
flexSource for Service tier (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Video generationOutput1$0.501M video tokens

Rate conditions

  1. Offline generation. Only successful video outputs billed. Actual completion_tokens determines charges; duration, frame rate and resolution affect usage.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Volcengine Ark video · default online inference

Provider source (opens in a new tab)
API model ID
doubao-seedance-1-0-pro-fast-251015
Access
Deprecated native route; existing endpoints until scheduled shutdown. No inference performed.
Regions
cn-beijing
API endpoint URL
POST https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasksSource for API endpoint URL (opens in a new tab)
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
VideoSource for Output modalities (opens in a new tab)

Synchronized audio is part of the generated video, not standalone speech synthesis.

Supported input workflows
Text to video, First frameSource for Supported input workflows (opens in a new tab)
Output resolutions
480p, 720p, 1080pSource for Output resolutions (opens in a new tab)
Frame rate
24 fpsSource for Frame rate (opens in a new tab)
Video duration
2–12 seconds through duration; frames allows supported fractional durations.Source for Video duration (opens in a new tab)
Output formats
mp4Source for Output formats (opens in a new tab)
Resolution controls
Default 1080p.Source for Resolution controls (opens in a new tab)
Reference asset limits
One first-frame image; no last-frame conditioning.Source for Reference asset limits (opens in a new tab)
Input image formats
jpeg, png, webp, bmp, tiff, gifSource for Input image formats (opens in a new tab)
Input image limits
Each image <30 MB; each side 300–6,000 px; width/height ratio 0.4–2.5.Source for Input image limits (opens in a new tab)
Request body limit
64 MB; large reference media should use URLs or asset IDs instead of Base64.Source for Request body limit (opens in a new tab)
Aspect ratios
16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptiveSource for Aspect ratios (opens in a new tab)

adaptive only for image-conditioned generation, not text-only generation.

Asynchronous generation
Create returns a task ID. Poll GET /api/v3/contents/generations/tasks/{id}, or receive callback_url status notifications.Source for Asynchronous generation (opens in a new tab)
Task record availability
Task records can be queried for seven days from creation. This is not a training-data retention commitment.Source for Task record availability (opens in a new tab)
Download URL lifetime
24 hours; download or transfer completed output promptly.Source for Download URL lifetime (opens in a new tab)
Task timeout
execution_expires_after: 3,600–259,200 seconds, default 172,800 (48 hours). Queued/running tasks exceeding this expire.Source for Task timeout (opens in a new tab)
Cancellation and task deletion
Only queued tasks may be cancelled; cancelled records are removed after 24 hours.Source for Cancellation and task deletion (opens in a new tab)
Duration discrepancy
GET duration is floor(actual frame count / 24). Do not use this rounded duration as the authoritative billing usage.Source for Duration discrepancy (opens in a new tab)
Visible watermark
watermark defaults to false; true adds a visible AI-generated mark.Source for Visible watermark (opens in a new tab)
Frame controls
return_last_frame=true returns a watermark-free JPEG at the output video dimensions.Source for Frame controls (opens in a new tab)
Billing basis
Successful videos only. Estimated video tokens = (input-video seconds + output-video seconds) × output width × output height × output fps / 1024. Actual billing uses usage.completion_tokens; these are video accounting units, not language tokens.Source for Billing basis (opens in a new tab)
Service tier
default online inferenceSource for Service tier (opens in a new tab)
Flex inference
SupportedSource for Flex inference (opens in a new tab)
Streaming
Not collected

Asynchronous polling/callbacks do not establish streaming video generation.

Batch processing
Not collected

Native flex inference is a video service tier, not proof of a general Batch API.

Output parameter range
frames: integers 29–289 satisfying 25+4n (positive integer n); takes priority over duration. 24 fps. These bounds do not apply to Seedance 2.x.Source for Output parameter range (opens in a new tab)
Random seed
seed=-1 for random, or integer through 2,147,483,647. Same seed gives similar, not guaranteed identical output.Source for Random seed (opens in a new tab)
Camera controls
camera_fixed defaults to false; true appends a fixed-camera instruction, without an effect guarantee.Source for Camera controls (opens in a new tab)
Published request quota
Online: 600 RPM, 10 concurrent. Flex: 500 billion video tokens/day; quotas are not rigid capacity guarantees.Source for Published request quota (opens in a new tab)
Endpoint availability
EOM September 24, 2026 at 10:00 UTC+8; EOS November 24, 2026 at 14:00 UTC+8. No automatic migration. Recommended replacement: doubao-seedance-2-0-mini-260615.Source for Endpoint availability (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Native video generationOnline video generation1CN¥4.201M video accounting tokens

Rate conditions

  1. 480p/720p/1080p; service_tier=default. Successful output only; video accounting tokens, not text tokens.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Volcengine Ark video (flex) · service_tier=flex; asynchronous offline video inference, 50% of online tariff. Cannot change tier after submission.

Provider source (opens in a new tab)
API model ID
doubao-seedance-1-0-pro-fast-251015
Access
Deprecated native route; existing endpoints until scheduled shutdown. No inference performed.
Regions
cn-beijing
API endpoint URL
POST https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasksSource for API endpoint URL (opens in a new tab)
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
VideoSource for Output modalities (opens in a new tab)

Synchronized audio is part of the generated video, not standalone speech synthesis.

Supported input workflows
Text to video, First frameSource for Supported input workflows (opens in a new tab)
Output resolutions
480p, 720p, 1080pSource for Output resolutions (opens in a new tab)
Frame rate
24 fpsSource for Frame rate (opens in a new tab)
Video duration
2–12 seconds through duration; frames allows supported fractional durations.Source for Video duration (opens in a new tab)
Output formats
mp4Source for Output formats (opens in a new tab)
Resolution controls
Default 1080p.Source for Resolution controls (opens in a new tab)
Reference asset limits
One first-frame image; no last-frame conditioning.Source for Reference asset limits (opens in a new tab)
Input image formats
jpeg, png, webp, bmp, tiff, gifSource for Input image formats (opens in a new tab)
Input image limits
Each image <30 MB; each side 300–6,000 px; width/height ratio 0.4–2.5.Source for Input image limits (opens in a new tab)
Request body limit
64 MB; large reference media should use URLs or asset IDs instead of Base64.Source for Request body limit (opens in a new tab)
Aspect ratios
16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptiveSource for Aspect ratios (opens in a new tab)

adaptive only for image-conditioned generation, not text-only generation.

Asynchronous generation
Create returns a task ID. Poll GET /api/v3/contents/generations/tasks/{id}, or receive callback_url status notifications.Source for Asynchronous generation (opens in a new tab)
Task record availability
Task records can be queried for seven days from creation. This is not a training-data retention commitment.Source for Task record availability (opens in a new tab)
Download URL lifetime
24 hours; download or transfer completed output promptly.Source for Download URL lifetime (opens in a new tab)
Task timeout
execution_expires_after: 3,600–259,200 seconds, default 172,800 (48 hours). Queued/running tasks exceeding this expire.Source for Task timeout (opens in a new tab)
Cancellation and task deletion
Only queued tasks may be cancelled; cancelled records are removed after 24 hours.Source for Cancellation and task deletion (opens in a new tab)
Duration discrepancy
GET duration is floor(actual frame count / 24). Do not use this rounded duration as the authoritative billing usage.Source for Duration discrepancy (opens in a new tab)
Visible watermark
watermark defaults to false; true adds a visible AI-generated mark.Source for Visible watermark (opens in a new tab)
Frame controls
return_last_frame=true returns a watermark-free JPEG at the output video dimensions.Source for Frame controls (opens in a new tab)
Billing basis
Successful videos only. Estimated video tokens = (input-video seconds + output-video seconds) × output width × output height × output fps / 1024. Actual billing uses usage.completion_tokens; these are video accounting units, not language tokens.Source for Billing basis (opens in a new tab)
Service tier
service_tier=flex; asynchronous offline video inference, 50% of online tariff. Cannot change tier after submission.Source for Service tier (opens in a new tab)
Flex inference
SupportedSource for Flex inference (opens in a new tab)
Streaming
Not collected

Asynchronous polling/callbacks do not establish streaming video generation.

Batch processing
Not collected

Native flex inference is a video service tier, not proof of a general Batch API.

Output parameter range
frames: integers 29–289 satisfying 25+4n (positive integer n); takes priority over duration. 24 fps. These bounds do not apply to Seedance 2.x.Source for Output parameter range (opens in a new tab)
Random seed
seed=-1 for random, or integer through 2,147,483,647. Same seed gives similar, not guaranteed identical output.Source for Random seed (opens in a new tab)
Camera controls
camera_fixed defaults to false; true appends a fixed-camera instruction, without an effect guarantee.Source for Camera controls (opens in a new tab)
Published request quota
Online: 600 RPM, 10 concurrent. Flex: 500 billion video tokens/day; quotas are not rigid capacity guarantees.Source for Published request quota (opens in a new tab)
Endpoint availability
EOM September 24, 2026 at 10:00 UTC+8; EOS November 24, 2026 at 14:00 UTC+8. No automatic migration. Recommended replacement: doubao-seedance-2-0-mini-260615.Source for Endpoint availability (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Native video generationOffline video generation1CN¥2.101M video accounting tokens

Rate conditions

  1. 480p/720p/1080p; service_tier=flex. Successful output only; video accounting tokens, not text tokens.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

BytePlus ModelArk · standard

seedance-1-0-pro-fast-251015
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

BytePlus ModelArk · flex

seedance-1-0-pro-fast-251015
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Volcengine Ark video · default online inference

doubao-seedance-1-0-pro-fast-251015
Not verified

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

How it works
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Minimum reusable input
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Lifetime & refresh
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

How to enable it
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Usage fields
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Billing rules
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Limits & data boundaries
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

Volcengine Ark video (flex) · service_tier=flex; asynchronous offline video inference, 50% of online tariff. Cannot change tier after submission.

doubao-seedance-1-0-pro-fast-251015
Not verified

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

How it works
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Minimum reusable input
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Lifetime & refresh
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

How to enable it
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Usage fields
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Billing rules
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

Limits & data boundaries
Not collected

No native prompt-cache contract or discounted cached-input tariff established. Draft reuse, stored assets and output retention are not prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred from the named native hosted API offering and cross-check of ByteDance and ByteDance-Seed public repositories. No matching downloadable checkpoint was found. This is not an explicit published weight-license declaration.

Classification evidence (opens in a new tab)

Lifecycle dates

Native Volcengine Seedance closed to new endpoints24 Sept 2026Source (opens in a new tab)
Native Volcengine Seedance shutdown scheduled at 14:00 UTC+824 Nov 2026Source (opens in a new tab)

Sources reviewed