What is the difference between wan2.7-image and wan2.7-image-pro?

Both share the same parameters and modes. wan2.7-image (standard) renders at 1K / 2K. wan2.7-image-pro is the higher-detail tier and supports text-to-image up to 4K; in editing and group modes the Pro tier caps at 2K. Pick Pro for hero and print work, standard for fast everyday generation.

How does Wan 2.7 Image pricing work?

Credit-based: 1 credit equals $0.001 USD. Wan 2.7 Image charges a flat rate per successfully generated image, independent of resolution and aspect ratio — so total cost is the per-image rate times your count (n). Failed and rejected requests are refunded automatically. See the pricing card above for the current per-image rate on each tier.

Does Wan 2.7 Image support image editing?

Yes. Pass reference images in image_urls and Wan 2.7 Image switches to editing mode — restyle, swap backgrounds, or fuse elements from up to nine images. URLs must be public HTTPS (no base64 or data: URIs); upload to your own storage first. The output aspect ratio follows your last reference image.

What is interactive editing with bbox_list?

bbox_list lets you target exact regions to edit or insert into. Each entry is a list of boxes in [x1, y1, x2, y2] absolute pixels (origin top-left), up to two per image, and the list runs parallel to image_urls (use [] to skip an image). It is API-driven inpainting without painting a mask.

How do I generate a consistent series?

Set enable_sequential to true to turn on group mode. Wan 2.7 Image then returns a connected set — same subject and style — and the count cap rises to 12. It is built for storyboards, comic panels, and campaign sets. Note that thinking mode and color palette do not apply in group mode.

Can Wan 2.7 Image render 4K?

4K is available on wan2.7-image-pro for text-to-image only. In editing and group modes, and on the standard tier, the maximum is 2K. Set resolution to 4K with the Pro model id and no reference images to render at full resolution.

Where is the full Wan 2.7 Image API reference?

The complete parameter list, modes, validation rules, error codes, and runnable cURL / Python / Node / Go examples for Wan 2.7 Image live at /docs/wan-2-7-image.

Wan Image API — Wan 2.7 Text-to-Image, Editing & 4K

Wan 2.7 Image is Alibaba's image model for generation and editing in one endpoint. Write a prompt for text-to-image, pass reference images to edit or fuse, box a region for precise interactive edits, or batch a consistent series — up to 4K on the Pro tier, all through reApi's OpenAI-compatible API.

Model type:

Price

Per image$0.0314/ 1 image

Standard tier. Text-to-image, editing, and multi-image reference at 1K / 2K.

Same API endpoint. The model parameter selects the variant.

Try Wan 2.7 Image View API Docs

01playground

InputsPOST /api/v1/images/generations

Prompt

Up to 5000 characters · required for text-to-image · optional (but recommended) when editing

Provide a prompt or at least one reference image / video / frame.

Reference images

Drag images here or click to upload

Public HTTPS URLs only (no base64) · up to 9 · output ratio follows the last image

Count1

1–4 normally · up to 12 in group mode · billed per generated image

Aspect ratio

1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 — pair with the resolution tier

Resolution

1K / 2K everywhere · 4K is Pro text-to-image only

Negative prompt

e.g. blurry, distorted, low quality

Watermark

Off by default

Seed

0–2147483647 · same seed + params gives a similar look

Thinking mode

On by default · only active for text-to-image with no reference and no group mode

Group mode

Raises the count cap to 12 · best for storyboards and comics

Edit regions (bbox)

JSON: [[[x1,y1,x2,y2], …≤2], …] — one entry per reference image, [] to skip

Color palette

JSON: 3–10 hex/ratio items summing to 100% · non-group mode only

Outputidle

try one of these prompts

02use cases

What you can build

Real workflows powered by this model.

Wan 2.7 Image text-to-image and editing examples

01/case

Generate and edit in one model

Wan 2.7 Image is a single endpoint for two jobs. Send a prompt and it renders text-to-image; add reference images and the same call switches to editing — restyle a product shot, swap a background, fuse elements from several photos into one scene. There is no separate edit model to learn: the request shape is identical, the mode is implicit in whether you attach images, and the output ratio follows your last reference.

Open the playground

Wan 2.7 Image interactive region editing with bounding boxes

02/case

Box a region for precise edits

Pass bbox_list and Wan 2.7 Image edits exactly where you point. Box the clock on the desk, the logo on the car, the empty wall — coordinates are absolute pixels on the source image, up to two regions each — and the model composites the change with matched lighting and perspective. It is interactive inpainting through the API, no mask painting required.

Wan 2.7 Image consistent multi-image series

03/case

Batch a consistent series

Turn on group mode and Wan 2.7 Image returns a connected set — same character, same style — across up to twelve frames in one call. It is built for storyboards, comic panels, and seasonal campaign sets where continuity matters. One request, one task ID, a coherent series back, with no outer loop to script or stitch.

03pricing

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

Category	Unit	Price
wan2.7-image
Per image	1 image	$0.03142857142857143 32 credits
wan2.7-image-pro
Per image	1 image	$0.07857142857142857 79 credits

05why

Why reAPI

One endpoint, every mode

Text-to-image, image editing, multi-image reference, interactive region edits, and group series all run through the same request to /api/v1/images/generations. Pick the tier with the model id — wan2.7-image or wan2.7-image-pro — and let the inputs decide the mode. No branching client code, no second model to integrate.

Up to 4K, credits in / image out

1 credit equals $0.001 USD. Wan 2.7 Image bills a flat rate per successfully generated image — independent of resolution and aspect ratio — so cost is a single multiply on your count. The Pro tier renders text-to-image up to 4K when you need print- and retina-grade detail; failed and rejected requests are never charged.

Async-first for production

Submit a Wan 2.7 Image task, get a task_id back, poll until it completes. It drops into the same task plumbing as every other reApi model, and the JSON matches the OpenAI image-generations contract — so adding Wan 2.7 Image is a model-id change, not a new integration.

06vs

Wan 2.7 Image vs Nano Banana Pro

Both generate and edit images from one API. Wan 2.7 Image leans into editing control — interactive region edits, multi-image fusion, consistent group series — with up to 4K and flat per-image pricing. Here is how the two compare on publicly documented behavior.

Capability

Wan 2.7 Image on reAPI

Nano Banana Pro

Generation + editing

One model, one request shape — text-to-image and editing switch automatically based on whether you attach reference images.

Generation and editing in one model, prompt-driven.

Interactive region edits

bbox_list targets exact pixel regions (up to two per image) — API-driven inpainting with no mask painting.

Region targeting is described in the prompt rather than by explicit coordinates.

Multi-image reference

Fuses up to nine reference images into one composition in a single call.

Accepts multiple reference images for blended edits.

Consistent series

Group mode returns up to twelve connected frames — same subject and style — in one request.

No documented single-call batch series; consistency is carried through follow-up prompts.

Resolution

1K / 2K everywhere; text-to-image up to 4K on the Pro tier.

Up to 4K output.

Pricing model

Flat per generated image, independent of resolution and aspect ratio; pay-as-you-go credits, no subscription.

Per-image pricing that scales with output resolution.

Comparison reflects publicly documented behavior at the time of writing. Model behavior and pricing can change; check the pricing card above and the API docs for current values.

07quickstart

Integrate Wan 2.7 Image in three steps

step 01
Create an API key
Sign up at reApi and grab a key. Free signup credits cover dozens of Wan 2.7 Image generations — enough to ship a first hero shot or edit before topping up.
Open
step 02
Submit a generation
POST to /api/v1/images/generations with model: wan2.7-image-pro (or wan2.7-image), a prompt, and optional size / resolution / image_urls. Wan 2.7 Image returns a task_id immediately.
Open
step 03
Poll the result
GET /api/v1/tasks/:id until status is completed. The Wan 2.7 Image response carries image URLs; mirror them to your own storage if you need them long term.
Open

08faq

Frequently asked questions

Common questions about this model.

Wan 2.7 Image is Alibaba's Wan image model for both generation and editing. It does text-to-image, image-to-image editing, multi-image reference fusion, interactive region edits, and consistent group series. On reApi it ships as two tiers — wan2.7-image (standard) and wan2.7-image-pro — on the OpenAI-compatible /api/v1/images/generations endpoint.

Related models

Explore more models in the same category.

View all models

Image

Google

Imagen 4.0

Imagen 4.0 — Google's text-to-image at a flat per-image rate across five aspect ratios.

From $0.046 per image

Image

ByteDance

Seedream 5.0 Lite

Seedream 5.0 Lite — Doubao image generation at 2K / 3K with image-to-image and batch output.

From $0.031 per image

Image

Google

Gemini 2.5 Flash Image Preview

Nano banana — fast Gemini image generation and editing, up to 14 reference images at 1K.

From $0.015 per image

Image

Google

Gemini 3.1 Flash Image Preview

Nano banana 2 — extreme ratio Gemini image generation with optional Google search grounding.

From $0.041 per image

View all models

10api reference

docs/api/wan-2-7-image

API reference

Drop-in code and the full parameter table.

View full reference

curl -X POST https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image-pro",
    "prompt": "a flower shop with delicate windows and a wooden door",
    "size": "16:9",
    "resolution": "2K"
  }'

start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.

Try Wan 2.7 Image Get API key

Wan Image API — Wan 2.7 Text-to-Image, Editing & 4K

What you can build

Real workflows powered by this model.

01/case