Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Wan 2.7

Wan 2.7 Image

Image generation, reference editing and coherent image sets, with up to 2K output.

availableClosed weightsImage generationImage editing
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
36 of 43 specification fields collected
Output resolutionUp to 2048×2048 total pixels in all modesSee specification notes below
Reference images99
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
Reasoning
SupportedSource for Reasoning (opens in a new tab)

thinking_mode defaults true, only for ordinary text-to-image generation with no reference image. It does not apply to image sets or editing.

Tool calling
Not supportedSource for Tool calling (opens in a new tab)

Singapore card scope. See individual regions for differences.

Structured output
Not supportedSource for Structured output (opens in a new tab)

Singapore card scope. See individual regions for differences.

Streaming
Not collected
Batch processing
Not supportedSource for Batch processing (opens in a new tab)

Singapore card scope. See individual regions for differences.

Fine-tuning
SupportedSource for Fine-tuning (opens in a new tab)

Singapore card scope. See individual regions for differences.

Knowledge cutoff
Not collected
Release date
2026-04-01Source for Release date (opens in a new tab)

Earliest reviewed regional release, not inferred from selector version.

Parameters
Not collected
Architecture
Not collected
Languages
Chinese, EnglishSource for Languages (opens in a new tab)

Documented prompt languages.

Context caching
Not supportedSource for Context caching (opens in a new tab)

Singapore card scope. See individual regions for differences.

Search grounding
Not supportedSource for Search grounding (opens in a new tab)

Singapore card scope. See individual regions for differences.

Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)

Singapore card scope. See individual regions for differences.

Maximum prompt characters
5,000Source for Maximum prompt characters (opens in a new tab)

Characters, not tokens. Excess prompt characters are truncated.

Visible watermark
Optional AI Generated 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)

The same seed does not guarantee identical output.

Output link expiry
Task data and image URLs are retained for 24 hours, then purgedSource for Output link expiry (opens in a new tab)

This is not a complete input retention or training-use policy.

Output billing
Charged per successfully generated image; input is free and failed calls do not consume paid or free quota.Source for Output billing (opens in a new tab)
Usage metering
Price × actual generated image count, not text tokensSource for Usage metering (opens in a new tab)
Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Asynchronous jobs use X-DashScope-Async: enable and task polling. Sync and async are transports of the same model.

Request mode
Single user message. Synchronous multimodal-generation and asynchronous image-generation APIs. Tokyo request URL remains unverified.Source for Request mode (opens in a new tab)
Input image limits
0–9 reference images; up to 20 MB each, 240–8,000 pixels per side and aspect ratio 1:8 to 8:1. Public URL or Base64.Source for Input image limits (opens in a new tab)
Input image formats
JPEG, JPG, PNG (no alpha), BMP, WEBPSource for Input image formats (opens in a new tab)
Images per request
Ordinary mode: n=1–4, default 1. Sequential mode: n is an upper bound of 1–12, default 12; actual output may be fewer.Source for Images per request (opens in a new tab)
Sequential image sets
enable_sequential=false by default; true generates a coherent image set with up to 12 outputs.Source for Sequential image sets (opens in a new tab)
Output resolutions
Up to 2048×2048 total pixels in all modesSource for Output resolutions (opens in a new tab)
Resolution controls
1K / 2K (default), or explicit width*height. No 4K mode.Source for Resolution controls (opens in a new tab)
Output resolutions
Custom total pixels: 768×768 to 2048×2048.Source for Output resolutions (opens in a new tab)
Aspect ratios
1:8 to 8:1; named size follows the last input image ratio, or square without input. Actual dimensions can vary slightly.Source for Aspect ratios (opens in a new tab)
Bounding-box placement
bbox_list aligns with input image order; at most two boxes per image, using original-image pixel coordinates [x1,y1,x2,y2].Source for Bounding-box placement (opens in a new tab)
Color palette control
3–10 HEX colors (8 recommended), ratios to two decimal places totaling 100.00%; only when sequential mode is disabled.Source for Color palette control (opens in a new tab)
Published availability regions
China (Beijing) · Chinese Mainland, Singapore · International, Japan (Tokyo) · GlobalSource 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
wan2.7-image
Access
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation (synchronous); image-generation/generation (asynchronous, X-DashScope-Async: enable). Async jobs poll /api/v1/tasks/{task_id}. Match workspace, region, API key and deployment scope.
Regions
Singapore
Published request quota
300 requests per minuteSource for Published request quota (opens in a new tab)
Task submission rate
5 requests per secondSource for Task submission rate (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)
Request mode
Synchronous and asynchronous image APIsSource for Request mode (opens in a new tab)
Free usage allowance
50 images; valid 90 days from latest activation, model release or approvalSource for Free usage allowance (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Image generationSuccessful output image1$0.03image

Rate conditions

  1. Published native USD list price per successfully generated image. International deployment. Actual generated image count determines cost; no token or text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Generated task/image data lasts 24 hours. Input retention, training use and regional enterprise terms remain unverified.

Alibaba Model Studio · China (Beijing) · Chinese Mainland

Provider source (opens in a new tab)
API model ID
wan2.7-image
Access
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation (synchronous); image-generation/generation (asynchronous, X-DashScope-Async: enable). Async jobs poll /api/v1/tasks/{task_id}. Match workspace, region, API key and deployment scope.
Regions
China (Beijing)
Published request quota
300 requests per minuteSource for Published request quota (opens in a new tab)
Task submission rate
5 requests per secondSource for Task submission rate (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)
Request mode
Synchronous and asynchronous image APIsSource for Request mode (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Image generationSuccessful output image1$0.027504image

Rate conditions

  1. Published native USD list price per successfully generated image. Chinese Mainland deployment. Actual generated image count determines cost; no token or text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Generated task/image data lasts 24 hours. Input retention, training use and regional enterprise terms remain unverified.

Alibaba Model Studio · Japan (Tokyo) · Global

Provider source (opens in a new tab)
API model ID
wan2.7-image
Access
Tokyo Global is documented by the model card; its request URL and regional transport contract are not verified in the reviewed image API. Confirm in the console before calling.
Regions
Japan (Tokyo)
Published request quota
300 requests per minuteSource for Published request quota (opens in a new tab)
Published tokens per minute
1,000,000Source for Published tokens per minute (opens in a new tab)

A quota counter, not a token billing price.

Request mode
Regional route/transport not collectedSource for Request mode (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Image generationSuccessful output image1$0.027504image

Rate conditions

  1. Published native USD list price per successfully generated image. Global deployment. Actual generated image count determines cost; no token or text-question estimate. This regional model-card rate is omitted from the reviewed central pricing table.
Pricing source (opens in a new tab)

Data & enterprise terms

Generated task/image data lasts 24 hours. Input retention, training use and regional enterprise terms remain unverified.

API model ID
akool/wan-2.7/text-to-image

Akool host selector. The nested model field explicitly names the Alibaba Wan 2.7 backend; no separate native Akool V2 weights are inferred.

Access
Choose Akool V2 in https://www.akool.com/apps/image-generator. Signed-in account, credits and feature entitlements apply.
Regions
Published personal-data storage: AWS in the EEA or United States unless otherwise specified. This is not a guarantee of a selectable inference region.
Declared backend
alibaba/wan-2.7/text-to-imageSource for Declared backend (opens in a new tab)
resolution
1k, 2kSource for resolution (opens in a new tab)

Default 2k; custom-size constraints are separate.

requestImages
img_count: 1–4, default 1. UI quantity catalog offers up to 16 with plan gates; do not silently treat 16 as the request-schema maximum.Source for requestImages (opens in a new tab)
parameterContract
{"aspect_ratio":{"configs":[{"label":"1:1","value":"1:1"},{"label":"4:3","value":"4:3"},{"label":"16:9","value":"16:9"},{"label":"3:4","value":"3:4"},{"label":"9:16","value":"9:16"}],"default":"1:1","enum":["1:1","4:3","16:9","3:4","9:16"],"required":false,"third_party_field":"scale","type":"string"},"extendFormSchema":[{"default":true,"label":"Thinking Mode","name":"thinking_mode","type":"switch","ui":{"tips":"Enable thinking mode for enhanced reasoning and better image quality. Increases generation time."}}],"height":{"default":2048,"required":false,"type":"number"},"img_count":{"default":1,"max":4,"min":1,"required":false,"type":"number"},"model":{"default":"alibaba/wan-2.7/text-to-image","required":true,"type":"string"},"negative_prompt":{"required":false,"type":"string"},"prompt":{"required":true,"type":"string"},"resolution":{"configs":[{"defaultHeight":1024,"defaultWidth":1024,"label":"1k","maxHeight":1024,"maxWidth":1024,"minHeight":768,"minWidth":768,"ratioLimits":{"16:9":{"maxHeight":765,"maxWidth":1360},"1:1":{"maxHeight":1024,"maxWidth":1024},"1:2":{"maxHeight":1448,"maxWidth":724},"1:3":{"maxHeight":1773,"maxWidth":591},"21:9":{"maxHeight":666,"maxWidth":1554},"2:1":{"maxHeight":724,"maxWidth":1448},"2:3":{"maxHeight":1254,"maxWidth":836},"3:1":{"maxHeight":591,"maxWidth":1773},"3:2":{"maxHeight":836,"maxWidth":1254},"3:4":{"maxHeight":1180,"maxWidth":885},"4:3":{"maxHeight":885,"maxWidth":1180},"4:5":{"maxHeight":1140,"maxWidth":912},"5:4":{"maxHeight":912,"maxWidth":1140},"9:16":{"maxHeight":1360,"maxWidth":765},"9:21":{"maxHeight":1554,"maxWidth":666}},"value":"1k"},{"default":true,"defaultHeight":2048,"defaultWidth":2048,"label":"2k","maxHeight":2048,"maxWidth":2048,"minHeight":768,"minWidth":768,"ratioLimits":{"16:9":{"maxHeight":1440,"maxWidth":2560},"1:1":{"maxHeight":1920,"maxWidth":1920},"1:2":{"maxHeight":2714,"maxWidth":1357},"1:3":{"maxHeight":3324,"maxWidth":1108},"21:9":{"maxHeight":1251,"maxWidth":2919},"2:1":{"maxHeight":1357,"maxWidth":2714},"2:3":{"maxHeight":2349,"maxWidth":1566},"3:1":{"maxHeight":1108,"maxWidth":3324},"3:2":{"maxHeight":1566,"maxWidth":2349},"3:4":{"maxHeight":2216,"maxWidth":1662},"4:3":{"maxHeight":1662,"maxWidth":2216},"4:5":{"maxHeight":2145,"maxWidth":1716},"5:4":{"maxHeight":1716,"maxWidth":2145},"9:16":{"maxHeight":2560,"maxWidth":1440},"9:21":{"maxHeight":2919,"maxWidth":1251}},"value":"2k"}],"default":"2k","enum":["1k","2k"],"required":false,"sizeRules":{"maxAspectRatio":8,"maxTotalPixels":16777216,"maxTotalPixelsImage2Image":4194304,"maxTotalPixelsText2Image":16777216,"minAspectRatio":0.125,"minTotalPixels":589824,"sizeSeparator":"*"},"supportsCustomSize":true,"type":"string"},"thinking_mode":{"default":true,"required":false,"type":"boolean"},"watermark":{"default":false,"required":false,"type":"boolean"},"width":{"default":2048,"required":false,"type":"number"}}Source for parameterContract (opens in a new tab)
creditMetadata
Catalog displays 1 credit for both 1k and 2k, with no explicit per-output denominator. Final charge for quantity/custom-size requests is unverified.Source for creditMetadata (opens in a new tab)
Training data policy
Published terms prohibit use of customer content or usage data to train machine-learning models.Source for Training data policy (opens in a new tab)
thinkingMode
Optional thinking_mode boolean, default true. This is image-generation reasoning configuration, not general text tool calling.Source for thinkingMode (opens in a new tab)

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

Data & enterprise terms

Terms state customer content and usage data will not be used by Akool or third parties to train machine-learning models. Privacy policy gives Customer Content a 365-day retention period with user deletion, and AWS storage in the EEA or US unless otherwise specified. Generated-resource expiry is separate from storage retention. Contract-specific and legal exceptions apply.

Read the service policy (opens in a new tab)
API model ID
akool/wan-2.7/image-to-image

Akool host selector. The nested model field explicitly names the Alibaba Wan 2.7 backend; no separate native Akool V2 weights are inferred.

Access
Choose Akool V2 in https://www.akool.com/apps/image-generator. Signed-in account, credits and feature entitlements apply.
Regions
Published personal-data storage: AWS in the EEA or United States unless otherwise specified. This is not a guarantee of a selectable inference region.
Declared backend
alibaba/wan-2.7/image-editSource for Declared backend (opens in a new tab)
resolution
1k, 2kSource for resolution (opens in a new tab)

Default 2k; custom-size constraints are separate.

requestImages
img_count: 1–4, default 1. UI quantity catalog offers up to 16 with plan gates; do not silently treat 16 as the request-schema maximum.Source for requestImages (opens in a new tab)
parameterContract
{"aspect_ratio":{"configs":[{"label":"1:1","value":"1:1"},{"label":"4:3","value":"4:3"},{"label":"16:9","value":"16:9"},{"label":"3:4","value":"3:4"},{"label":"9:16","value":"9:16"}],"default":"1:1","enum":["1:1","4:3","16:9","3:4","9:16"],"required":false,"third_party_field":"scale","type":"string"},"height":{"default":2048,"required":false,"type":"number"},"images":{"maxItems":9,"minItems":1,"required":true,"type":"array"},"img_count":{"default":1,"max":4,"min":1,"required":false,"type":"number"},"model":{"default":"alibaba/wan-2.7/image-edit","required":true,"type":"string"},"negative_prompt":{"required":false,"type":"string"},"prompt":{"required":true,"type":"string"},"resolution":{"configs":[{"defaultHeight":1024,"defaultWidth":1024,"label":"1k","maxHeight":1024,"maxWidth":1024,"minHeight":768,"minWidth":768,"ratioLimits":{"16:9":{"maxHeight":765,"maxWidth":1360},"1:1":{"maxHeight":1024,"maxWidth":1024},"1:2":{"maxHeight":1448,"maxWidth":724},"1:3":{"maxHeight":1773,"maxWidth":591},"21:9":{"maxHeight":666,"maxWidth":1554},"2:1":{"maxHeight":724,"maxWidth":1448},"2:3":{"maxHeight":1254,"maxWidth":836},"3:1":{"maxHeight":591,"maxWidth":1773},"3:2":{"maxHeight":836,"maxWidth":1254},"3:4":{"maxHeight":1180,"maxWidth":885},"4:3":{"maxHeight":885,"maxWidth":1180},"4:5":{"maxHeight":1140,"maxWidth":912},"5:4":{"maxHeight":912,"maxWidth":1140},"9:16":{"maxHeight":1360,"maxWidth":765},"9:21":{"maxHeight":1554,"maxWidth":666}},"value":"1k"},{"default":true,"defaultHeight":2048,"defaultWidth":2048,"label":"2k","maxHeight":2048,"maxWidth":2048,"minHeight":768,"minWidth":768,"ratioLimits":{"16:9":{"maxHeight":1440,"maxWidth":2560},"1:1":{"maxHeight":1920,"maxWidth":1920},"1:2":{"maxHeight":2714,"maxWidth":1357},"1:3":{"maxHeight":3324,"maxWidth":1108},"21:9":{"maxHeight":1251,"maxWidth":2919},"2:1":{"maxHeight":1357,"maxWidth":2714},"2:3":{"maxHeight":2349,"maxWidth":1566},"3:1":{"maxHeight":1108,"maxWidth":3324},"3:2":{"maxHeight":1566,"maxWidth":2349},"3:4":{"maxHeight":2216,"maxWidth":1662},"4:3":{"maxHeight":1662,"maxWidth":2216},"4:5":{"maxHeight":2145,"maxWidth":1716},"5:4":{"maxHeight":1716,"maxWidth":2145},"9:16":{"maxHeight":2560,"maxWidth":1440},"9:21":{"maxHeight":2919,"maxWidth":1251}},"value":"2k"}],"default":"2k","enum":["1k","2k"],"required":false,"sizeRules":{"maxAspectRatio":8,"maxTotalPixels":4194304,"maxTotalPixelsImage2Image":4194304,"maxTotalPixelsText2Image":16777216,"minAspectRatio":0.125,"minTotalPixels":589824,"sizeSeparator":"*"},"supportsCustomSize":true,"type":"string"},"ui":{"assetsTips":"Select reference image (up to 9 pics, 20mb)"},"watermark":{"default":false,"required":false,"type":"boolean"},"width":{"default":2048,"required":false,"type":"number"}}Source for parameterContract (opens in a new tab)
creditMetadata
Catalog displays 1 credit for both 1k and 2k, with no explicit per-output denominator. Final charge for quantity/custom-size requests is unverified.Source for creditMetadata (opens in a new tab)
Training data policy
Published terms prohibit use of customer content or usage data to train machine-learning models.Source for Training data policy (opens in a new tab)
Reference images
1–9 reference images; UI tip says 20 MB. Catalog does not clearly establish whether this size applies per file or in aggregate.Source for Reference images (opens in a new tab)

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

Data & enterprise terms

Terms state customer content and usage data will not be used by Akool or third parties to train machine-learning models. Privacy policy gives Customer Content a 365-day retention period with user deletion, and AWS storage in the EEA or US unless otherwise specified. Generated-resource expiry is separate from storage retention. Contract-specific and legal exceptions apply.

Read the service policy (opens in a new tab)

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.

Akool web app

akool/wan-2.7/text-to-image
Not verified

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

How it works
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Minimum reusable input
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Lifetime & refresh
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

How to enable it
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Usage fields
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Billing rules
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Limits & data boundaries
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

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

Caching reviewed 14 Oct 2026

Akool web app

akool/wan-2.7/image-to-image
Not verified

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

How it works
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Minimum reusable input
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Lifetime & refresh
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

How to enable it
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Usage fields
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Billing rules
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

Limits & data boundaries
Not collected

Saved media, avatar templates, voice assets and temporary result URLs do not establish prompt caching or discounted cached-input pricing.

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

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: a separately documented native image API release has no exact checkpoint in the reviewed official Wan-AI public-weight inventory. Public Wan video checkpoints are not evidence of the image model weights. Private lineage, parameters and architecture remain unknown.

Classification evidence (opens in a new tab)

Lifecycle dates

Platform release · Singapore1 Apr 2026Source (opens in a new tab)
Platform release · China (Beijing)1 Apr 2026Source (opens in a new tab)
Platform release · Japan (Tokyo)1 Apr 2026Source (opens in a new tab)

Sources reviewed