Qwen-Image — hosted API access
This repository is not the model weights — it documents running Qwen-Image through a hosted API on apimodels.app, a multi-model gateway where one key and one OpenAI-compatible endpoint reach 110+ image, video, audio and language models.
- Original model & weights: https://huggingface.co/Qwen/Qwen-Image
- Authors: the Qwen team (Alibaba)
- License: Apache-2.0
Independent hosted-API integration. Not affiliated with or endorsed by the authors; does not redistribute their weights. All credit for the model is theirs.
What it does
A strong open image model, notably good at rendering readable text and complex layouts. Generate 1K/2K images from a prompt.
A sample produced through the apimodels.app API.
Use it via API
On apimodels.app the model is served as qwen3-image (base) and qwen3-image-pro (higher quality). Get a key at https://apimodels.app, then:
# text-to-image (sync: pass a WxH size, get the image inline)
curl -X POST https://api.apimodels.app/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" \
-d '{ "model": "qwen3-image", "prompt": "a cozy bookstore cafe, warm light", "size": "1360x768" }'
Pricing
| Tier | Price |
|---|---|
| qwen3-image, 1K/2K | $0.034 / image |
| qwen3-image-pro, 1K | $0.045 |
| qwen3-image-pro, 2K | $0.085 |
Failed jobs are not charged. Result files are kept for 7 days.
Links
- Run it: apimodels.app
- Original model: https://huggingface.co/Qwen/Qwen-Image