Image

Wan 2.7 Image API

Wan 2.7 Image API (wan2.7-image) on APIMart runs the standard edition of Alibaba's Wan 2.7 image model. It handles text to image, image editing, multi-image reference with up to 9 inputs, bounding-box editing and sequential sets of up to 12 images, at 1K or 2K, billed per generated image.

Text to ImageImage EditingUp to 9 References1K / 2K

Get API Key API Docs

Service Highlights

Official Discounts
Pay-as-you-go
Fast & Low Latency

Input

Model

Input Images (optional)

Prompt

101 / 5000

Negative Prompt

Resolution

Aspect Ratio

Number of Images

Seed (optional)

Content Moderation

Watermark

Sequential Mode

Generate a series of coherent images (up to 12)

Thinking Mode

Enhanced reasoning for better quality (text-to-image only)

Color Palette

3–10 color stops with ratios summing to 100% (non-sequential only)

Output

Image link valid for 72 hours

Wan 2.7 Image API Pricing

Transparent pricing with no hidden fees. Pay only for what you use.

Variant	GoldCurrent price	Platinum	Diamond	Official	Your savings
`wan2.7-image`	0.216Credits(~$0.0216)/pic	0.2052Credits(~$0.0205)/pic	0.1944Credits(~$0.0194)/pic	0.27Credits(~$0.027)/pic	20%

* Actual costs are subject to final output.

Wan 2.7 Image API - Alibaba wan2.7-image Generation and Editing

Use the Wan 2.7 Image API on APIMart to generate images from text, edit them with up to 9 reference images or selected regions, and create coherent sets of up to 12 images at 1K or 2K, billed per image.

Get API Key

50K+

Active Users

99.9%

Uptime

Faster

20%

Cost Savings

Key Features of the Wan 2.7 Image API

What the standard wan2.7-image model does across generation and editing

Text to Image with the Wan 2.7 Image API

Write a prompt of up to 5,000 characters and choose 1K or 2K with 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 or 2:3, or exact pixel dimensions.

Image Editing from a Prompt

Add image_urls to switch to editing. The output aspect ratio follows the last input image.

Multi-Image Reference with up to 9 Images

Combine elements from several inputs, such as a product and a scene, in one request.

Interactive Editing with Bounding Boxes

Mark up to 2 regions per input image with bbox_list to edit or insert content exactly where you want it.

Sequential Sets of up to 12 Images

Turn on enable_sequential to generate a thematically coherent set, such as storyboard panels or a product series.

Custom Color Palettes

Pass 3 to 10 hex colors with ratios that add up to 100% to keep images on brand.

Thinking Mode for Text to Image

thinking_mode is on by default for text to image without sequential mode, trading longer generation for better results.

Billed per Image, Not by Resolution

You pay per successfully generated image. Resolution and aspect ratio do not change the price, and failed requests are free.

What You Can Build with the Wan 2.7 Image API

Everyday image workflows at up to 2K

Product Photos in New Settings

Edit a product shot into a new background or lifestyle scene from one prompt.

Element Fusion from Several Images

Merge a character, a product and a location from separate references into one image.

Precise Region Edits

Change or add objects only inside selected boxes and leave the rest of the image untouched.

Storyboards and Comic Panels

Generate up to 12 consistent images in one request for sequences and series.

On-Brand Social Graphics

Keep campaign visuals inside your brand colors with a custom palette.

Fast Drafts Before Final Art

Iterate on ideas at 1K or 2K, then move a chosen concept to Wan 2.7 Image Pro for 4K.

How to Get a Wan 2.7 Image API Key and Start Building

From sign-up to your first Wan 2.7 Image result in three steps

Create Your Wan 2.7 Image API Key

→

Test Wan 2.7 Image in the Playground

Try text-to-image and editing above and check the cost per image before you write code.

→

Integrate the Wan 2.7 Image API

Submit tasks from your backend with the example below, then poll for the result.

Get API Key

Wan 2.7 Image API Example: Text to Image and Image Editing

Call the Wan 2.7 Image API on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint for the image URL.

1
Authenticate Wan 2.7 Image requests
Save your APIMart key in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
2
Submit a Wan 2.7 Image task
POST /v1/images/generations with model wan2.7-image, your prompt, size and resolution. Add image_urls to edit. The task ID is in data[0].task_id.
3
Get the Wan 2.7 Image result
Poll GET /v1/tasks/{task_id} until status is completed, then read the image URL from data.result.images[0].url[0] and save the file to your own storage.
See the Wan 2.7 Image API reference for every parameter, editing rule and response field.

POST /v1/images/generations

curl -X POST https://api.apimart.ai/v1/images/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image",
    "prompt": "A cozy flower shop window at dawn, wooden door, buckets of tulips on display, soft morning light, photorealistic",
    "n": 1,
    "size": "16:9",
    "resolution": "2K"
  }'

import os
import time
import requests

API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}

# 1. Submit the generation task
payload = {
  "model": "wan2.7-image",
  "prompt": "A cozy flower shop window at dawn, wooden door, buckets of tulips on display, soft morning light, photorealistic",
  "n": 1,
  "size": "16:9",
  "resolution": "2K"
}
resp = requests.post(f"{API_BASE}/v1/images/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]

# 2. Poll the task until it finishes
for _ in range(200):
    task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
    task_resp.raise_for_status()
    task = task_resp.json()["data"]
    if task["status"] == "completed":
        print(task["result"]["images"][0]["url"][0])
        break
    if task["status"] == "failed":
        raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
    time.sleep(3)
else:
    raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")

curl -X POST https://api.apimart.ai/v1/images/generations \
  -H "Authorization: Bearer $APIMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image",
    "prompt": "Place the product on a marble kitchen counter beside fresh lemons, soft daylight, keep the label unchanged",
    "n": 1,
    "image_urls": [
      "https://example.com/product.jpg"
    ],
    "resolution": "2K"
  }'

TASK_ID="task_xxx"  # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
  -H "Authorization: Bearer $APIMART_API_KEY"

Wan 2.7 Image API Parameters

Parameter	Type	Required	Default	Description
`model`	string	Required	Default: wan2.7-image	Use wan2.7-image.
`prompt`	string	Required	Default: —	Image description, up to 5,000 characters. Optional but recommended when editing.
`image_urls`	array	Optional	Default: —	Up to 9 input images (URL or Base64; JPEG, PNG, WEBP or BMP; 240–8000 px; up to 20 MB each). Switches to editing; the output ratio follows the last image.
`n`	integer	Optional	Default: 1	Images per request: 1–4, or 1–12 with enable_sequential. Billed per image.
`size`	string	Optional	Default: 2K	1K or 2K, an aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3) or pixel dimensions.
`resolution`	string	Optional	Default: —	1K or 2K. Can be combined with an aspect ratio in size.
`negative_prompt`	string	Optional	Default: —	Elements to avoid.
`enable_sequential`	boolean	Optional	Default: false	Generate a coherent set of images, such as a storyboard. Max n is 12.
`bbox_list`	array	Optional	Default: —	Edit regions per input image, up to 2 boxes each; pass [] for images without a box.
`color_palette`	array	Optional	Default: —	3–10 hex colors with ratios that sum to 100%. Not used in sequential mode.
`thinking_mode`	boolean	Optional	Default: true	Enhanced reasoning for quality, at the cost of time. Text to image without sequential mode only.
`seed`	integer	Optional	Default: —	0 to 2147483647 for consistent results with identical parameters.
`watermark`	boolean	Optional	Default: false	Add an AI Generated watermark in the bottom-right corner.
`nsfw_check`	boolean	Optional	Default: false	Moderate the prompt and input images with omni-moderation-latest before submission.

Customer Stories by Wan

See how creators use wan2.7 image generation to transform their workflows. See how Wan teams ship faster. These are original Wan 2.7 Image series reviews and may refer to different versions.

“wan2.7 image generation delivers quality that honestly surprised me. The color accuracy and texture detail are exceptional — we use it daily for product campaigns.”

Alex Chen

Creative Director at DesignWorks

“The Wan API is refreshingly simple. I integrated wan2.7 image generation into our platform in an hour. Reliability via APIMart is rock solid.”

Sarah Mitchell

UI/UX Designer

“wan2.7 image generation picks up subtle stylistic cues that other wan2.7 image generation models miss. Clients ask how I generate Wan outputs so fast.”

Marcus Weber

Freelance Illustrator

“APIMart's pricing for Wan is unbeatable. We generate hundreds of visuals per week with wan2.7 image generation and the cost is a fraction of what we paid before.”

Emma Rodriguez

Marketing Manager

“Switching to wan2.7 image generation from other Wan models is just a swap. No API changes needed across the Wan lineup.”

James Liu

Full-Stack Developer

“We rely on wan2.7 image generation for all campaign concepting. Outstanding Wan speed-to-quality — we scale output with wan2.7 image generation fast.”

Sophie Anderson

Art Director at AdVision

Compare Wan 2.7 Image Models

Both Wan 2.7 Image models use the same request format and are billed per image on APIMart. Pick by the resolution and detail you need.

Model	Best for	Resolution
Wan 2.7 Image APIThis page	Everyday text to image, editing and sets at up to 2K, at a lower price per image	1K / 2K
Wan 2.7 Image Pro API	Detailed text to image up to 4K, plus editing and sets at up to 2K	1K / 2K / 4K

Wan 2.7 Image API FAQ

Answers about wan2.7-image, how it compares with Pro and how to call it

What is Wan 2.7 Image (wan2.7-image)?

Wan 2.7 Image is the standard edition of Alibaba's Wan 2.7 image model. It supports text to image, image editing, multi-image reference, interactive editing and sequential generation at up to 2K. On APIMart its model ID is wan2.7-image.

What is the difference between Wan 2.7 Image and Wan 2.7 Image Pro?

Wan 2.7 Image Pro (wan2.7-image-pro) adds 4K for text to image and is described in the docs as having better detail; editing and sequential sets stay at up to 2K for both. Wan 2.7 Image is the faster standard edition and costs less per image.

Is Wan 2.7 Image the same as the Wan 2.7 video model?

No. Wan 2.7 Image (wan2.7-image) creates still images. The Wan 2.7 API for video is the separate wan2.7 model, which has its own page.

How do I edit images with Wan 2.7 Image?

Add one or more images to image_urls and describe the change in the prompt. To edit specific areas, add bbox_list with up to 2 boxes per image, using absolute pixel coordinates from the top-left corner.

How many reference images can I use?

Up to 9 images per request: JPEG, PNG, WEBP or BMP, 240 to 8000 pixels per side, aspect ratio between 1:8 and 8:1, and up to 20 MB each.

Can Wan 2.7 Image generate several images at once?

Yes. n generates 1 to 4 images in standard mode. With enable_sequential on, n can go up to 12 and the images form a coherent set; thinking_mode and color_palette are ignored in that mode.

What resolutions and aspect ratios does Wan 2.7 Image support?

1K or 2K (default 2K) in every mode, from 768×768 to 2048×2048 pixels. size also accepts 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 and 2:3, or pixel dimensions such as 1024x1024.

What parameters does the Wan 2.7 Image API support?

model (wan2.7-image) is required, and prompt is required for text to image. Optional fields: image_urls, n, size, resolution, negative_prompt, enable_sequential, bbox_list, color_palette, thinking_mode, seed, watermark and nsfw_check.

How do I call the Wan 2.7 Image API and get the result?

POST to /v1/images/generations and read the task ID from data[0].task_id. Poll GET /v1/tasks/{task_id} until status is completed, then read data.result.images[0].url[0].

How much does the Wan 2.7 Image API cost?

Wan 2.7 Image is billed per successfully generated image. Resolution and aspect ratio do not change the price, and the estimate is the unit price times n. See the pricing table on this page; Gold members save 20%, and Platinum and Diamond members save up to 28%.

Is Wan 2.7 Image free or open source?

No. APIMart has no free quota for Wan 2.7 Image; you pay per generated image. Alibaba offers Wan 2.7 as a hosted API and has not released its weights, so there is no official download.

How do I get a Wan 2.7 Image API key?

Sign up for APIMart, add balance and create a key on the API Keys page. Send it as Authorization: Bearer <key>. The same key works for every Wan model and the rest of the APIMart catalog.

Related Models

Explore more models in the same category.

View All Models →

Wan 2.7 Image API

Wan 2.7 Image API Pricing

Wan 2.7 Image API - Alibaba wan2.7-image Generation and Editing

Key Features of the Wan 2.7 Image API

What You Can Build with the Wan 2.7 Image API

How to Get a Wan 2.7 Image API Key and Start Building

Create Your Wan 2.7 Image API Key

Test Wan 2.7 Image in the Playground

Integrate the Wan 2.7 Image API

Wan 2.7 Image API Example: Text to Image and Image Editing

Authenticate Wan 2.7 Image requests

Submit a Wan 2.7 Image task

Get the Wan 2.7 Image result

Wan 2.7 Image API Parameters

Customer Stories by Wan

Compare Wan 2.7 Image Models

Wan 2.7 Image API FAQ

What is Wan 2.7 Image (wan2.7-image)?

What is the difference between Wan 2.7 Image and Wan 2.7 Image Pro?

Is Wan 2.7 Image the same as the Wan 2.7 video model?

How do I edit images with Wan 2.7 Image?

How many reference images can I use?

Can Wan 2.7 Image generate several images at once?

What resolutions and aspect ratios does Wan 2.7 Image support?

What parameters does the Wan 2.7 Image API support?

How do I call the Wan 2.7 Image API and get the result?

How much does the Wan 2.7 Image API cost?

Is Wan 2.7 Image free or open source?

How do I get a Wan 2.7 Image API key?

Related Models

Latest Wan 2.7 Image articles

Key Features of the Wan 2.7 Image API

What You Can Build with the Wan 2.7 Image API

How to Get a Wan 2.7 Image API Key and Start Building

Create Your Wan 2.7 Image API Key

Test Wan 2.7 Image in the Playground

Integrate the Wan 2.7 Image API

Customer Stories by Wan

Wan 2.7 Image API FAQ

What is Wan 2.7 Image (wan2.7-image)?

What is the difference between Wan 2.7 Image and Wan 2.7 Image Pro?

Is Wan 2.7 Image the same as the Wan 2.7 video model?

How do I edit images with Wan 2.7 Image?

How many reference images can I use?

Can Wan 2.7 Image generate several images at once?

What resolutions and aspect ratios does Wan 2.7 Image support?

What parameters does the Wan 2.7 Image API support?

How do I call the Wan 2.7 Image API and get the result?

How much does the Wan 2.7 Image API cost?

Is Wan 2.7 Image free or open source?

How do I get a Wan 2.7 Image API key?

Related Models