Z-Image Turbo API
Z-Image Turbo is a 6B-parameter, 8-step open-source text-to-image model. Alibaba Cloud states that it ranked first among open-source text-to-image models on Artificial Analysis, with strong Chinese/English text rendering and 120 RPM.
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": "z-image-turbo",
"prompt": "A red panda reading under a cedar tree",
"size": "1024x1024",
"n": 1
}'Where it fits
Best for
- High-volume image generation and variants
- Rapid ideation and thumbnails
- Cost-sensitive text rendering
Tradeoffs
- Less premium than the Pro image models
- Use a premium model for final hero assets
Model details
FAQ
What makes Z-Image Turbo notable?
It uses only 6B parameters and 8 inference steps, and Alibaba Cloud states it ranked first among open-source text-to-image models on Artificial Analysis.
Does prompt enhancement cost more?
The catalog shows a separate enhanced-output price. Check the model page for the current rate.
How do I call this model?
Use KimiSeek's OpenAI-compatible API and set the model field to z-image-turbo with your KimiSeek API key.