Wan 2.7 Image Pro

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)

Output modalities

ImageSource for Output modalities (opens in a new tab)

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.

Console model playground

SupportedSource for Console model playground (opens in a new tab)

API aliases

wan2.7-image-proSource for API aliases (opens in a new tab)

Maximum prompt characters

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

Characters, not tokens. Excess prompt characters are truncated.

Output formats

PNGSource for Output formats (opens in a new tab)

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)

Image-to-image editing

SupportedSource for Image-to-image editing (opens in a new tab)

Reference images

9Source for Reference images (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 4096×4096 total pixels for ordinary text-to-image; up to 2048×2048 for editing and image setsSource for Output resolutions (opens in a new tab)

Resolution controls

1K / 2K (default) / 4K, or explicit width*height. 4K requires no image input and sequential mode disabled.Source for Resolution controls (opens in a new tab)

Output resolutions

Custom total pixels: 768×768 to 4096×4096 for ordinary text-to-image; 768×768 to 2048×2048 otherwise.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 · InternationalSource for Published availability regions (opens in a new tab)

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

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

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.

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.

Lifecycle dates

Sources reviewed