license: apache-2.0
language:
- en
tags:
- text-to-image
- z-image
- api
- apimodels
- not-for-all-audiences
- nsfw
Z-Image — hosted API access
This repository is not the model weights — it documents running Z-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/Tongyi-MAI/Z-Image
- Authors: Tongyi-MAI (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 fast, efficient open text-to-image model. This page exposes it as the z-image-spicy tiers on the API —
the relaxed-moderation ("Spicy") line, so outputs may include adult content and the repository carries the
not-for-all-audiences tag. The API is for adults only; the model's own safety systems still apply upstream.
A sample produced through the apimodels.app API.
Use it via API
On apimodels.app the model is served as z-image-spicy and z-image-spicy-pro. 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": "z-image-spicy", "prompt": "a cozy bookstore cafe, warm light", "size": "1360x768" }'
Pricing
| Tier | Price |
|---|---|
| z-image-spicy | $0.015 / image (flat) |
| z-image-spicy-pro | $0.03 / image (flat) |
Failed jobs are not charged. Result files are kept for 7 days.
Links
- Run it: apimodels.app
- Original model: https://huggingface.co/Tongyi-MAI/Z-Image