Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Wan 2.1

Wan 2.1 Text to Image Plus

Text-to-image generation with Chinese and English prompts, optional prompt rewriting and explicit image dimensions.

availableClosed weightsImage generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
31 of 39 specification fields collected
Output resolutionDefault 1024 × 1024; each side 512–1,440 pixelsSee specification notes below
Text input limit500500
Input billingSee ratesAlibaba Model Studio · Beijing
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
Streaming
Not collected
Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
API aliases
wanx2.1-t2i-plus, wan2.1-t2i-plusSource for API aliases (opens in a new tab)

Beijing and Singapore service selectors, not interchangeable IDs. Grouped by provider version/tier; binary checkpoint equivalence is unverified.

Published availability regions
China (Beijing), SingaporeSource for Published availability regions (opens in a new tab)
Prompt limits
500 characters; Chinese characters and letters count individually, and excess input is truncated.Source for Prompt limits (opens in a new tab)
Images per request
1–4; default 4Source for Images per request (opens in a new tab)
Request mode
Asynchronous HTTP submission with X-DashScope-Async: enable; poll task ID for results. SDK wrappers may wait synchronously for that async job.Source for Request mode (opens in a new tab)
Random seed range
0–2,147,483,647; omitted seed is random. Reusing a seed is not an exact-reproducibility guarantee.Source for Random seed range (opens in a new tab)
Visible watermark
Optional lower-right AI-generated watermark; false by default.Source for Visible watermark (opens in a new tab)
Output link expiry
Task IDs and generated image URLs expire after 24 hours. This does not establish input retention or training-use policy.Source for Output link expiry (opens in a new tab)
Usage metering
Per successfully generated output image. CNY and USD listings use different billing-market schedules, not a currency conversion.Source for Usage metering (opens in a new tab)
Free usage allowance
Domestic-account listing: 500 Beijing images for 90 days from latest activation, release or approval, no Singapore quota. International-account listing: 200 Singapore images with the same 90-day date basis; no Beijing quota. Account eligibility unverified.Source for Free usage allowance (opens in a new tab)

International-account terms come from the separate international billing page, not a combined worldwide allowance.

Required request fields
input.prompt is required. Reference-image editing is not part of this text-to-image contract.Source for Required request fields (opens in a new tab)
Output resolutions
Default 1024 × 1024; each side 512–1,440 pixelsSource for Output resolutions (opens in a new tab)
Prompt rewriting
prompt_extend=true by default; an LLM rewrites the prompt and adds processing time.Source for Prompt rewriting (opens in a new tab)
Generated assets
Generated-image URLs, retrieved by task IDSource for Generated assets (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 · Beijing

Provider source (opens in a new tab)
API model ID
wanx2.1-t2i-plus
Access
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis. Asynchronous HTTP submission with X-DashScope-Async: enable; poll task ID for results. SDK wrappers may wait synchronously for that async job.
Regions
China (Beijing)
Published request quota
120 requests per minuteSource for Published request quota (opens in a new tab)
Task submission rate
2 submissions per secondSource for Task submission rate (opens in a new tab)
Concurrent requests
2 running tasksSource for Concurrent requests (opens in a new tab)
Request mode
Asynchronous HTTP submission with X-DashScope-Async: enable; poll task ID for results. SDK wrappers may wait synchronously for that async job.Source for Request mode (opens in a new tab)
Free usage allowance
Domestic-account listing: 500 Beijing images for 90 days from latest activation, release or approval, no Singapore quota. International-account listing: 200 Singapore images with the same 90-day date basis; no Beijing quota. Account eligibility unverified.Source for Free usage allowance (opens in a new tab)

International-account terms come from the separate international billing page, not a combined worldwide allowance.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Domestic-account CNY listing · BeijingGenerated image1CN¥0.20image
International-account USD listing · BeijingGenerated image1$0.028671image

Rate conditions

  1. Published per-output-image tariff for the named billing market and deployment region; not a currency conversion. Free quota and eligibility vary by billing market.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Result links expire after 24 hours. Input retention, training use and actual account entitlement remain unverified.

Alibaba Model Studio · Singapore

Provider source (opens in a new tab)
API model ID
wan2.1-t2i-plus
Access
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis. Asynchronous HTTP submission with X-DashScope-Async: enable; poll task ID for results. SDK wrappers may wait synchronously for that async job.
Regions
Singapore
Published request quota
120 requests per minuteSource for Published request quota (opens in a new tab)
Task submission rate
2 submissions per secondSource for Task submission rate (opens in a new tab)
Concurrent requests
2 running tasksSource for Concurrent requests (opens in a new tab)
Request mode
Asynchronous HTTP submission with X-DashScope-Async: enable; poll task ID for results. SDK wrappers may wait synchronously for that async job.Source for Request mode (opens in a new tab)
Free usage allowance
Domestic-account listing: 500 Beijing images for 90 days from latest activation, release or approval, no Singapore quota. International-account listing: 200 Singapore images with the same 90-day date basis; no Beijing quota. Account eligibility unverified.Source for Free usage allowance (opens in a new tab)

International-account terms come from the separate international billing page, not a combined worldwide allowance.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Domestic-account CNY listing · SingaporeGenerated image1CN¥0.366962image
International-account USD listing · SingaporeGenerated image1$0.05image

Rate conditions

  1. Published per-output-image tariff for the named billing market and deployment region; not a currency conversion. Free quota and eligibility vary by billing market.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Result links expire after 24 hours. Input retention, training use and actual account entitlement remain unverified.

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.

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

Qualified classification inference: this separately named native image API is not an exact checkpoint in the reviewed official Wan-AI inventory. Public Wan2.1 T2V weights can also perform text-to-image generation, so task overlap alone neither proves equivalence nor proves private weights. The specific hosted Plus/Turbo/Flash/editing checkpoint lineage remains unverified; public video architecture and parameter counts are not copied.

Classification evidence (opens in a new tab)

Lifecycle dates

Beijing Model Studio release9 Jan 2025Source (opens in a new tab)
Singapore / international service release22 May 2025Source (opens in a new tab)

Sources reviewed