Alibaba: Wan2.7 Image
wan2-7-image- Price
- From $0.03
- Modalities
- Image
About Wan2.7 Image
Wan2.7 Image is Alibaba's image model that generates and edits pictures in one system, announced in April 2026 alongside Wan2.7 video. It handles text-to-image, instruction-based editing, multi-image composition, and click-to-select editing of single elements. Alibaba highlights facial feature customisation, colour palette control from supplied colour codes, and long text rendering in 12 languages. The standard version sits below Wan2.7 Image Pro.
Where it works well
- One model covers text-to-image and instruction-based editing, so a generated image can be refined without switching tools.
- Accepts up to nine reference images in a request and can return up to 12 images at once, useful for storyboards and product sets.
- Colour palette control lets you supply specific colour codes and proportions to match brand colours.
- Renders long text from lengthy prompts across 12 languages, including formulas and tables according to Alibaba.
When to choose another model
- The Pro version is the one Alibaba lists for sharper prompt interpretation, steadier composition, and 4K output, so choose Pro for final production images.
- Click-to-edit style selection needs an interface that sends the selected region; a plain prompt call cannot point at pixels.
- It creates still images only; Wan 2.7 or Wan 3.0 are the Wan options for video.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Image editingText to imageTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "image-to-image", "model": "wan2-7-image", "prompt": "A minimalist product photo of matte black headphones on a soft blue background.", "image_url": "https://example.com/source.png" }'
Pricing
Official price is the model maker's public baseline. TokenLab price is what you pay for this model on TokenLab.
Image editing
per image- Official price
- $0.03
- Official
- $0.03
- Discount
- —
Text to image
per image- Official price
- $0.03
- Official
- $0.03
- Discount
- —
| Official priceper image | Officialper image | Discount | |
|---|---|---|---|
| Image editing | $0.03 | $0.03 | — |
| Text to image | $0.03 | $0.03 | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Wan2.7 Image in Console with a prompt ready to edit or send.
Help me create an image with wan2-7-image using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Storyboards and image series
Generate several related frames in one request from a set of reference images so characters and style stay consistent across panels.
Brand-coloured marketing visuals
Provide the brand colour codes and proportions, and generate banners that follow the palette instead of drifting to default hues.
Posters with real text
Create layouts with headlines, tables, or short paragraphs in Chinese, English, or another supported language and inspect the lettering at full size.
Virtual avatar design
Adjust facial structure and eye shape of a virtual character, then render it in different scenes.
Prompt examples
A flat-lay of a coffee bag, cup, and beans on a cream linen cloth, palette: #3B2A20 as the main color, #E8D9C5 as the secondary, #C8553D as a small accent.
Four-panel storyboard of a courier crossing a rainy night market, same character in every panel, soft neon light.
A conference poster titled 'Quantum Materials 2026' with a three-row schedule table, English and Chinese text.
FAQ
What can Wan2.7 Image do?
It generates images from text, edits images from instructions, composes several reference images into one result, and supports click-to-edit for individual elements. Alibaba also lists colour palette input, avatar face customisation, and long multilingual text rendering.
How is Wan2.7 Image different from Wan2.7 Image Pro?
Alibaba positions Pro as the upgrade with more stable composition, sharper prompt interpretation, and 4K output. The standard model has the same feature set and suits drafts and volume work, while Pro suits final assets where layout accuracy matters.
How many images can it take and return?
According to Alibaba's announcement, one request can use up to nine reference images and produce up to 12 output images. That makes it practical for storyboards, product angle sets, and character sheets.
Does it render text inside images?
Yes. Alibaba says it accepts very long text prompts and renders print-quality text in 12 languages, including formulas and tables, so posters and slides can carry real copy.
Can I control colours precisely?
Yes. The colour palette feature accepts specific colour codes with proportions, so generated images follow a brand scheme. You can also extract a palette from a reference image and apply it to new ones.
How much does Wan2.7 Image cost?
On TokenLab, Wan2.7 Image costs $0.03 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should Wan2.7 Image use?
Use https://api.tokenlab.sh/v1/images/edits for Wan2.7 Image. The request example below shows the matching code shape.
Which operations does Wan2.7 Image support?
Wan2.7 Image supports Image editing, Text to image. Select an operation above to see its endpoint and request example.
Compare Wan2.7 Image
Sources
Reviewed Oct 2, 2026
