Wan 2.7 Image Pro API

Wan2.7-Image Pro is the precision tier of Wan2.7: text and multi-image reference input, instruction-based editing, up to nine references and twelve outputs, 3000-token text input, 12 languages and 4K output.

Mode Image APIMax output —From ¥0.4 / image

Official source: model page · verified 2026-10-22

Create an account Read the docs

PRICING

Pricing

CNY / usage-based

ItemCNY

Reference image¥0

Output image¥0.4

Prices can change with upstream providers; the rate at settlement is authoritative.

QUICKSTART

Call the API

Use the OpenAI-compatible endpoint; no model-specific SDK setup is required.

Shell

curl https://api.kimiseek.app/v1/images/generations \
  -H "Authorization: Bearer $KIMISEEK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image-pro",
    "prompt": "A red panda reading under a cedar tree",
    "size": "1024x1024",
    "n": 1
  }'

FIT

Where it fits

Best for

High-fidelity campaign and hero visuals
Multi-reference character and product work
Storyboards and e-commerce sets

Tradeoffs

Premium per-image pricing
Use Wan2.7-Image for drafts and volume

DETAILS

Model details

One API keyCNY billingImage APIPay as you go

FAQ

Is Wan2.7-Image Pro only text-to-image?

No. It supports text plus multiple reference images, instruction editing and batch outputs. Pro adds 4K output.

How many references can it use?

The official announcement says up to nine reference images and up to twelve generated images.

How do I call this model?

Use KimiSeek's OpenAI-compatible API and set the model field to wan2.7-image-pro with your KimiSeek API key.