Alibaba Cloud / Wan 2.6

Wan 2.6 Image to Video

First-frame video generation, with synchronized audio and multi-shot controls.

Video generation

availableClosed weightsVideo generation

Official documentation (opens in a new tab)Reviewed 14 Oct 2026
36 of 44 specification fields collected

Output resolution720P, 1080PSee specification notes below

Clip duration2–15 secondsSee specification notes below

Input billingSee ratesAlibaba Model Studio · Singapore · International

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
Input modalities: Text, Image, AudioSource for Input modalities (opens in a new tab)
Output modalities: Video, AudioSource for Output modalities (opens in a new tab)
Reasoning: Not collected
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Streaming: Not collected
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Knowledge cutoff: Not collected
Release date: 2025-12-03Source for Release date (opens in a new tab)
Parameters: Not collected
Architecture: Not collected
Languages: Chinese, EnglishSource for Languages (opens in a new tab)
Context caching: Not supportedSource for Context caching (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Console model playground: SupportedSource for Console model playground (opens in a new tab)
API aliases: wan2.6-i2vSource for API aliases (opens in a new tab)
Maximum prompt characters: 1,500Source for Maximum prompt characters (opens in a new tab)
Negative prompts: At most 500 characters; excess input is truncatedSource for Negative prompts (opens in a new tab)
Frame rate: 30Source for Frame rate (opens in a new tab)
Output formats: MP4 (H.264)Source for Output formats (opens in a new tab)
Video duration: 2–15 secondsSource for Video duration (opens in a new tab)
Output resolutions: 720P, 1080PSource for Output resolutions (opens in a new tab)
Default resolution: 1080PSource for Default resolution (opens in a new tab)
Videos per request: 1Source for Videos per request (opens in a new tab)
Visible watermark: Optional API watermark, off by defaultSource for Visible watermark (opens in a new tab)
Random seed range: 0–2,147,483,647; omitted selects a random seedSource for Random seed range (opens in a new tab)
Request mode: Legacy DashScope video-synthesis protocol; submit with X-DashScope-Async: enable, then poll /api/v1/tasks/{task_id}Source for Request mode (opens in a new tab)
Task ID lifetime: 24 hours for task queriesSource for Task ID lifetime (opens in a new tab)
Output link expiry: Result URL expires after 24 hours; save generated video promptlySource for Output link expiry (opens in a new tab)
Audio input limits: Public WAV/MP3 URL, 3–30 seconds, at most 15 MB. Audio longer than the output is trimmed; shorter audio leaves a silent tail.Source for Audio input limits (opens in a new tab)
Prompt rewriting: On by default; optional. Wan 2.6 shot_type only takes effect when prompt_extend is true.Source for Prompt rewriting (opens in a new tab)
Generation controls: shot_type single/default or multi; requires prompt_extend=true and overrides shot instructions in the promptSource for Generation controls (opens in a new tab)
Output billing: Generated output-video duration only; input is free. Failed requests are not billed.Source for Output billing (opens in a new tab)
Image input limits: One first-frame image, at most 20 MB; 240–8,000 pixels per side; public URL or Base64Source for Image input limits (opens in a new tab)
Image input formats: JPEG, JPG, PNG (no alpha), BMP, WEBPSource for Image input formats (opens in a new tab)
Aspect ratios: Output approximates the source image ratio; select a resolution tier with resolutionSource for Aspect ratios (opens in a new tab)
Required request fields: img_url is required; prompt and audio_url are optionalSource for Required request fields (opens in a new tab)
Source audio handling: Uses supplied audio or generates synchronized sound. An audio=false switch is not documented for this selector.Source for Source audio handling (opens in a new tab)
Published availability regions: Singapore · International, China (Beijing) · Chinese Mainland, Germany (Frankfurt) · Global, US (Virginia) · Global, US (Virginia) · USSource for Published availability regions (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.

Alibaba Model Studio · Singapore · International

Provider source (opens in a new tab)

API model ID: wan2.6-i2v
Access: POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis; poll /api/v1/tasks/{task_id}. Match the model, region, API key and deployment scope.
Regions: Singapore
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Context caching: Not supportedSource for Context caching (opens in a new tab)
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Console model playground: SupportedSource for Console model playground (opens in a new tab)
Input modalities: Image, Text, AudioSource for Input modalities (opens in a new tab)
Output modalities: Video, AudioSource for Output modalities (opens in a new tab)
Published request quota: 300 requests per minuteSource for Published request quota (opens in a new tab)
Request quotas: 300 RPM in the model cardSource for Request quotas (opens in a new tab)
Regional processing: Deployment scope: InternationalSource for Regional processing (opens in a new tab)
Free usage allowance: 50 seconds; 90 days from latest activation, release or application approvalSource for Free usage allowance (opens in a new tab)
Task submission rate: 5 requests per secondSource for Task submission rate (opens in a new tab)
Concurrent requests: 5Source for Concurrent requests (opens in a new tab)
Quota scope: Primary account aggregate across RAM users, workspaces and API keys; each model has its own quotaSource for Quota scope (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Video generation	720P with audio · output¹	$0.10	second
Video generation	1080P with audio · output¹	$0.15	second

Rate conditions

Generated output-video duration only; input is free. Failed requests are not billed. International deployment. Native published USD rate, without exchange-rate conversion. No text-token or per-question estimate.

Pricing source (opens in a new tab)

Data & enterprise terms

Task/result links expire after 24 hours. This does not establish regional training-use, retention or enterprise account terms.

Alibaba Model Studio · China (Beijing) · Chinese Mainland

Provider source (opens in a new tab)

API model ID: wan2.6-i2v
Access: POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis; poll /api/v1/tasks/{task_id}. Match the model, region, API key and deployment scope.
Regions: China (Beijing)
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Context caching: Not supportedSource for Context caching (opens in a new tab)
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Console model playground: SupportedSource for Console model playground (opens in a new tab)
Input modalities: Image, Text, AudioSource for Input modalities (opens in a new tab)
Output modalities: Video, AudioSource for Output modalities (opens in a new tab)
Published request quota: 300 requests per minuteSource for Published request quota (opens in a new tab)
Request quotas: 300 RPM in the model cardSource for Request quotas (opens in a new tab)
Regional processing: Deployment scope: Chinese MainlandSource for Regional processing (opens in a new tab)
Task submission rate: 5 requests per secondSource for Task submission rate (opens in a new tab)
Concurrent requests: 5Source for Concurrent requests (opens in a new tab)
Quota scope: Primary account aggregate across RAM users, workspaces and API keys; each model has its own quotaSource for Quota scope (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Video generation	720P with audio · output¹	$0.086012	second
Video generation	1080P with audio · output¹	$0.143353	second

Rate conditions

Generated output-video duration only; input is free. Failed requests are not billed. Chinese Mainland deployment. Native published USD rate, without exchange-rate conversion. No text-token or per-question estimate.

Pricing source (opens in a new tab)

Data & enterprise terms

Task/result links expire after 24 hours. This does not establish regional training-use, retention or enterprise account terms.

Alibaba Model Studio · Germany (Frankfurt) · Global

Provider source (opens in a new tab)

API model ID: wan2.6-i2v
Access: POST https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis; poll /api/v1/tasks/{task_id}. Match the model, region, API key and deployment scope.
Regions: Germany (Frankfurt)
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Context caching: Not supportedSource for Context caching (opens in a new tab)
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Console model playground: Not supportedSource for Console model playground (opens in a new tab)
Input modalities: Image, Text, AudioSource for Input modalities (opens in a new tab)
Output modalities: Video, AudioSource for Output modalities (opens in a new tab)
Published request quota: 300 requests per minuteSource for Published request quota (opens in a new tab)
Request quotas: 300 RPM in the model cardSource for Request quotas (opens in a new tab)
Regional processing: Global inference scope; endpoint location does not mean region-confined inferenceSource for Regional processing (opens in a new tab)
Task submission rate: 5 requests per secondSource for Task submission rate (opens in a new tab)
Concurrent requests: 5Source for Concurrent requests (opens in a new tab)
Quota scope: Primary account aggregate across RAM users, workspaces and API keys; each model has its own quotaSource for Quota scope (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Video generation	720P with audio · output¹	$0.086012	second
Video generation	1080P with audio · output¹	$0.143353	second

Rate conditions

Generated output-video duration only; input is free. Failed requests are not billed. Global deployment. Native published USD rate, without exchange-rate conversion. No text-token or per-question estimate.

Pricing source (opens in a new tab)

Data & enterprise terms

Task/result links expire after 24 hours. This does not establish regional training-use, retention or enterprise account terms.

Alibaba Model Studio · US (Virginia) · Global

Provider source (opens in a new tab)

API model ID: wan2.6-i2v
Access: POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis; poll /api/v1/tasks/{task_id}. Match the model, region, API key and deployment scope. Global and US scopes have separate tariffs; confirm workspace scope selection before calling.
Regions: US (Virginia)
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Context caching: Not supportedSource for Context caching (opens in a new tab)
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Console model playground: SupportedSource for Console model playground (opens in a new tab)
Input modalities: Image, Text, AudioSource for Input modalities (opens in a new tab)
Output modalities: Video, AudioSource for Output modalities (opens in a new tab)
Published request quota: 60 requests per minuteSource for Published request quota (opens in a new tab)
Request quotas: 60 RPM in the model cardSource for Request quotas (opens in a new tab)
Regional processing: Global inference scope; endpoint location does not mean region-confined inferenceSource for Regional processing (opens in a new tab)
Task submission rate: 5 requests per secondSource for Task submission rate (opens in a new tab)
Concurrent requests: 5Source for Concurrent requests (opens in a new tab)
Quota scope: Primary account aggregate across RAM users, workspaces and API keys; each model has its own quotaSource for Quota scope (opens in a new tab)
Published quota differences: Card: 60 RPM; central page: 5 RPS and 5 concurrent tasks. Separate published constraints, not an inferred conversion; confirm the effective account allowance.Source for Published quota differences (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Video generation	720P with audio · output¹	$0.086012	second
Video generation	1080P with audio · output¹	$0.143353	second

Rate conditions

Generated output-video duration only; input is free. Failed requests are not billed. Global deployment. Native published USD rate, without exchange-rate conversion. No text-token or per-question estimate.

Pricing source (opens in a new tab)

Data & enterprise terms

Task/result links expire after 24 hours. This does not establish regional training-use, retention or enterprise account terms.

Alibaba Model Studio · US (Virginia) · US

Provider source (opens in a new tab)

API model ID: wan2.6-i2v
Access: POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis; poll /api/v1/tasks/{task_id}. Match the model, region, API key and deployment scope. Global and US scopes have separate tariffs; confirm workspace scope selection before calling.
Regions: US (Virginia)
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Context caching: Not supportedSource for Context caching (opens in a new tab)
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Console model playground: SupportedSource for Console model playground (opens in a new tab)
Input modalities: Image, Text, AudioSource for Input modalities (opens in a new tab)
Output modalities: Video, AudioSource for Output modalities (opens in a new tab)
Published request quota: 6000 requests per minuteSource for Published request quota (opens in a new tab)
Request quotas: 6000 RPM in the model cardSource for Request quotas (opens in a new tab)
Regional processing: US deployment scope, distinct from Virginia GlobalSource for Regional processing (opens in a new tab)
Task submission rate: 5 requests per secondSource for Task submission rate (opens in a new tab)
Concurrent requests: 5Source for Concurrent requests (opens in a new tab)
Quota scope: Primary account aggregate across RAM users, workspaces and API keys; each model has its own quotaSource for Quota scope (opens in a new tab)
Published quota differences: Card: 6000 RPM; central page: 5 RPS and 5 concurrent tasks. Separate published constraints, not an inferred conversion; confirm the effective account allowance.Source for Published quota differences (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Video generation	720P with audio · output¹	$0.10	second
Video generation	1080P with audio · output¹	$0.15	second

Rate conditions

Generated output-video duration only; input is free. Failed requests are not billed. US deployment. Native published USD rate, without exchange-rate conversion. No text-token or per-question estimate.

Pricing source (opens in a new tab)

Data & enterprise terms

Task/result links expire after 24 hours. This does not establish regional training-use, retention or enterprise account terms.

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.

Alibaba Model Studio · Singapore · International

wan2.6-i2v

Not supported

Support evidence (opens in a new tab)Caching reviewed 14 Oct 2026

Alibaba Model Studio · China (Beijing) · Chinese Mainland

wan2.6-i2v

Not supported

Support evidence (opens in a new tab)Caching reviewed 14 Oct 2026

Alibaba Model Studio · Germany (Frankfurt) · Global

wan2.6-i2v

Not supported

Support evidence (opens in a new tab)Caching reviewed 14 Oct 2026

Alibaba Model Studio · US (Virginia) · Global

wan2.6-i2v

Not supported

Support evidence (opens in a new tab)Caching reviewed 14 Oct 2026

Alibaba Model Studio · US (Virginia) · US

wan2.6-i2v

Not supported

Support evidence (opens in a new tab)Caching reviewed 14 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

Classification inference: this native Wan 2.5/2.6 API release is separately documented and has no exact checkpoint in the reviewed official Wan-AI public-weight inventory. Public Wan 2.1/2.2 checkpoints are excluded. API availability and inventory absence do not prove private checkpoint lineage; undisclosed parameter counts and architecture are not borrowed from public models.

Classification evidence (opens in a new tab)

Lifecycle dates

Platform release · Singapore · International3 Dec 2025Source (opens in a new tab)

Platform release · US (Virginia) · Global3 Dec 2025Source (opens in a new tab)

Platform release · China (Beijing)3 Dec 2025Source (opens in a new tab)

Platform release · Germany (Frankfurt) · Global3 Dec 2025Source (opens in a new tab)

Sources reviewed

Official Wan documentation: wan26 i2v card (opens in a new tab)Reviewed 14 Oct 2026

Official Wan documentation: wan legacy i2v api (opens in a new tab)Reviewed 14 Oct 2026

Official Wan documentation: pricing (opens in a new tab)Reviewed 14 Oct 2026

Official Wan documentation: release (opens in a new tab)Reviewed 14 Oct 2026

Official Wan documentation: overview (opens in a new tab)Reviewed 14 Oct 2026

Official Wan documentation: weights (opens in a new tab)Reviewed 14 Oct 2026

Official Wan documentation: site (opens in a new tab)Reviewed 14 Oct 2026

Official Wan documentation: wan rate limits (opens in a new tab)Reviewed 14 Oct 2026