Qwen Image 3.0 Pro API
Qwen Image 3.0 Pro is the premium image generation and editing model in the Qwen Image line. The official page highlights up to 4.5K-token image input, dense layouts, 10px text, 12-language text rendering and 1K/2K output tiers.
Official source: model page · verified 2026-10-22
Pricing
Prices can change with upstream providers; the rate at settlement is authoritative.
Call the API
Use the OpenAI-compatible endpoint; no model-specific SDK setup is required.
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-pro",
"prompt": "A red panda reading under a cedar tree",
"size": "1024x1024",
"n": 1
}'Where it fits
Best for
- Dense layouts such as posters, menus and storyboards
- Small-text rendering and multilingual graphics
- Reference-guided image editing
Tradeoffs
- 2K outputs move into a higher per-image tier
- Use Qwen Image 3.0 for early drafts
Model details
FAQ
Why does the price change by resolution?
The model prices 1K and 2K outputs differently. Check the model page before generating large batches.
Does it support reference images?
Yes. The official page lists image and text input; the current API price table shows a separate reference-image rate.
How do I call this model?
Use KimiSeek's OpenAI-compatible API and set the model field to qwen-image-3.0-pro with your KimiSeek API key.