Wan 2.7 Image API

Wan2.7-Image is the standard tier of Wan2.7, combining text and multi-image reference input with instruction editing, up to nine references and twelve outputs. It is designed for high-volume creative work before moving final assets to Pro.

Mode Image APIMax output —From ¥0.16 / 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¥0.16

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",
    "prompt": "A red panda reading under a cedar tree",
    "size": "1024x1024",
    "n": 1
  }'

FIT

Where it fits

Best for

Concept exploration and moodboards
Multi-image campaign drafts
Illustration and social content

Tradeoffs

Less precise than the Pro tier
Use Pro for 4K and final high-fidelity assets

DETAILS

Model details

One API keyCNY billingImage APIPay as you go

FAQ

What is the difference from Pro?

The standard tier targets cost and iteration; Pro adds 4K output and higher-fidelity positioning.

Can it edit with reference images?

Yes. The official Wan2.7 announcement describes multi-image reference and instruction-based editing.

How do I call this model?

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