Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Wanx image generation

Wanx v1

Chinese and English text-to-image generation with optional reference-image content or style guidance.

availableClosed weightsImage generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
32 of 40 specification fields collected
Output resolution1024 × 1024 (default), 720 × 1280, 768 × 1152, 1280 × 720See specification notes below
Text input limit800800
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
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)

API documents reference images in addition to the card’s text-only summary.

Reasoning
Not collected
Streaming
Not collected
Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Published availability regions
China (Beijing)Source for Published availability regions (opens in a new tab)
Request mode
Asynchronous HTTP task submission with X-DashScope-Async: enable, followed by result queries. Not evidence of Batch API support.Source for Request mode (opens in a new tab)
Published price
CNY 0.16 per generated image.Source for Published price (opens in a new tab)
Usage metering
Output-image billing. No token tariff or USD conversion is inferred.Source for Usage metering (opens in a new tab)
Prompt limits
Positive prompt: at most 800 characters; negative prompt: at most 500. Each Chinese character or letter counts as one; excess is truncated.Source for Prompt limits (opens in a new tab)
Required request fields
A positive prompt; optional reference image.Source for Required request fields (opens in a new tab)
Image input limits
Reference: 256–4,096 pixels per side, at most 10 MB.Source for Image input limits (opens in a new tab)
Input image formats
JPG, JPEG, PNG, BMP, TIFF, WEBPSource for Input image formats (opens in a new tab)
Image URL requirements
Reference URL must not contain Chinese characters.Source for Image URL requirements (opens in a new tab)
Image styles
<auto> (default), <photography>, <portrait>, <3d cartoon>, <anime>, <oil painting>, <watercolor>, <sketch>, <chinese painting>, <flat illustration>Source for Image styles (opens in a new tab)
Output resolutions
1024 × 1024 (default), 720 × 1280, 768 × 1152, 1280 × 720Source for Output resolutions (opens in a new tab)
Images per request
1–4; default 4Source for Images per request (opens in a new tab)
Generation controls
ref_strength: 0–1; no verified default. ref_mode: repaint (default, content) or refonly (style). seed: 0–2,147,483,647; omitted seed is random, and multi-image outputs use successive seeds. Reuse improves stability, not a guarantee of identical output.Source for Generation controls (opens in a new tab)
Output link expiry
Task IDs and generated image URLs are valid for 24 hours; input retention is not established.Source for Output link expiry (opens in a new tab)
Free usage allowance
500 images. API says 180 days after activation; central pricing says 90 days from the latest activation, release or approval. Account entitlement unverified.Source for Free usage allowance (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
wanx-v1
Access
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis. Asynchronous HTTP task submission with X-DashScope-Async: enable, followed by result queries. Not evidence of Batch API support.
Regions
China (Beijing)
Task submission rate
2 submissions per secondSource for Task submission rate (opens in a new tab)
Quota scope
Per-model limits shared by the Alibaba Cloud account and RAM usersSource for Quota scope (opens in a new tab)
Free usage allowance
500 images. API says 180 days after activation; central pricing says 90 days from the latest activation, release or approval. Account entitlement unverified.Source for Free usage allowance (opens in a new tab)
Request mode
Asynchronous HTTP task submission with X-DashScope-Async: enable, followed by result queries. Not evidence of Batch API support.Source for Request mode (opens in a new tab)
Published request quota
120 requests per minuteSource for Published request quota (opens in a new tab)
Published token quota
3,000 tokens per minuteSource for Published token quota (opens in a new tab)

Not a context window or token tariff.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Wanx v1Generated image1CN¥0.16image

Rate conditions

  1. Published Beijing image tariff. No converted USD amount or text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Input retention, training use and account entitlement are not verified. Documented task/result expiry is not a full policy.

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: a separately named native Alibaba hosted model/API. Reviewed official sources document inference access but identify no exact downloadable checkpoint. This does not prove that no public release exists; private checkpoint lineage remains under review. Public Wan weights and research model sizes are not assumed equivalent.

Classification evidence (opens in a new tab)

Lifecycle dates

Model Studio release5 Jan 2024Source (opens in a new tab)

Sources reviewed