Skip to content
Model infoModelsSnapshot: 15 Oct 2026

ByteDance / Seedance

Seedance 1.0 Lite I2V (250428)

Historical Seedance Lite image-to-video model, supporting first and last frames or one to four reference images.

retiredClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
5 of 23 specification fields collected
Output resolution480p, 720p, 1080pSee specification notes below
Clip durationNot collectedAwaiting source review
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 input tokens
Not collected
Maximum output
Not collected
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
Video duration
Not collected
Frame rate
Not collected
Output formats
Not collected
Output resolutions
480p, 720p, 1080pSource for Output resolutions (opens in a new tab)
Release month
June 2025Source for Release month (opens in a new tab)

The release log gives a month, not a day. The 250428 selector suffix is not treated as the release date.

Published request quota
300 requests/minute; 5 concurrent generation requests per primary account and model versionSource for Published request quota (opens in a new tab)

Historical documented quotas. Excess concurrent requests queue; excess RPM fails task creation. Not a current service offer.

Access & pricing

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

BytePlus ModelArk · Historical native video generation

Provider source (opens in a new tab)
API model ID
seedance-1-0-lite-i2v-250428
Access
Historical endpoint. BytePlus service ended on May 13, 2026; no new requests are available through this retired route.
Regions
Not collected
Service tier
Historical native video generationSource for Service tier (opens in a new tab)
API aliases
bytedance-seedance-1-0-lite-i2v-250428Source for API aliases (opens in a new tab)

Selector spelling in the retirement notice; the model card omits this prefix.

Supported input workflows
First frame with optional last frame and optional text prompt, One to four reference images with optional text promptSource for Supported input workflows (opens in a new tab)
Request size limit
300 RPM; 5 concurrent tasks per primary account/version; extra concurrent tasks queueSource for Request size limit (opens in a new tab)

Historical card quotas, not guaranteed contemporary account entitlements.

Generation mode
Asynchronous: create a generation task, then query its ID for the resultSource for Generation mode (opens in a new tab)
Reference images
1–4 reference imagesSource for Reference images (opens in a new tab)
Last-frame control
SupportedSource for Last-frame control (opens in a new tab)

Optional last frame in the first-frame workflow.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Historical video generationImage-to-video generation1$1.801M video tokens

Rate conditions

  1. Historical card price, not a current offer: BytePlus service ended May 13, 2026. Same rate published for T2V and I2V. Video-token accounting is distinct from text tokens; no clip-total formula or cost per question is inferred.
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 (retired)

Provider source (opens in a new tab)
API model ID
doubao-seedance-1-0-lite-i2v-250428
Access
Retired native route. No current inference access is represented.
Regions
cn-beijing
Endpoint availability
Native service ended May 11, 2026 at 14:00 UTC+8. The eighth-batch table specifies replacement by doubao-seedance-2-0-fast-260128. This is the older notice, distinct from later no-migration notices.Source for Endpoint availability (opens in a new tab)
Pricing coverage
Not collected

Historical native CNY price not established. International historical USD rates are not copied.

Release identity
Native Doubao selector grouped with the corresponding international family, dated revision and task. Identical deployed weights are not independently established.Source for Release identity (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

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 · Historical native video generation

seedance-1-0-lite-i2v-250428
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.

Caching reviewed 15 Oct 2026

Volcengine Ark (retired)

doubao-seedance-1-0-lite-i2v-250428
Not verified

No version-specific prompt-cache contract or tariff established.

How it works
Not collected

No version-specific prompt-cache contract or tariff established.

Minimum reusable input
Not collected

No version-specific prompt-cache contract or tariff established.

Lifetime & refresh
Not collected

No version-specific prompt-cache contract or tariff established.

How to enable it
Not collected

No version-specific prompt-cache contract or tariff established.

Usage fields
Not collected

No version-specific prompt-cache contract or tariff established.

Billing rules
Not collected

No version-specific prompt-cache contract or tariff established.

Limits & data boundaries
Not collected

No version-specific prompt-cache contract or tariff established.

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

BytePlus deprecation announced17 Mar 2026Source (opens in a new tab)
BytePlus new endpoint creation ended23 Mar 2026Source (opens in a new tab)
BytePlus service ended13 May 2026Source (opens in a new tab)
Volcengine native new endpoint creation ended9 Apr 2026Source (opens in a new tab)
Volcengine native service ended at 14:00 UTC+811 May 2026Source (opens in a new tab)

Sources reviewed