Qwen Image 3.0 API

Qwen Image 3.0 is the standard image model in the Qwen Image line. It supports up to 4.5K-token instructions, stable 10px text, 12-language rendering and daily image production at a lower per-image cost than Pro.

Mode Image APIMax output —From ¥0.144 / image

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

Create an account Read the docs

PRICING

Pricing

CNY / usage-based

ItemCNY

Reference image¥0.016

Output image¥0.144

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": "qwen-image-3.0",
    "prompt": "A red panda reading under a cedar tree",
    "size": "1024x1024",
    "n": 1
  }'

FIT

Where it fits

Best for

Daily social and content images
Posters, pages and interface mockups
Cost-sensitive image iteration

Tradeoffs

Less premium positioning than Qwen Image 3.0 Pro
Use Pro for the densest layouts and highest-fidelity work

DETAILS

Model details

One API keyCNY billingImage APIPay as you go

FAQ

What can Qwen Image 3.0 render?

The official page highlights 10px text, 12 languages, multiple fonts and complex image-text instructions.

When should I use Pro?

When the image is a final asset and dense layout or higher-resolution fidelity matters.

How do I call this model?

Use KimiSeek's OpenAI-compatible API and set the model field to qwen-image-3.0 with your KimiSeek API key.