Try Z-Image for low-cost Chinese-friendly portraits, signage, city scenes, and food photography with five ratios, real examples, and API code.
Provider: Alibaba
Category: image generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Try Z-Image for low-cost Chinese-friendly portraits, signage, city scenes, and food photography with five ratios, real examples, and API code.
Pricing
Standard Usage
Ready for generation
Configure your parameters and click "Run" to see the output here.
Fast commercial generation
Compare four-step output, readable English text, seed control, and low per-image cost.
Try Z-Image for low-cost Chinese-friendly portraits, signage, city scenes, and food photography with five ratios, real examples, and API code.
The Playground and API use the same model ID: z-image. This endpoint accepts text prompts only; reference-image editing uses the separate Image-to-Image route.
These specifications reflect the current Z-Image request contract.
Final cost depends on the output tier and input add-ons. Check the live page price and task record for the final charge.
Choose the destination and aspect ratio before composing subject, scene, material, light, and text.
Copy a minimal request below. See Docs for parameters, callbacks, task retrieval, and errors.
POST /v1/tasksz-imagecurl -X POST https://api.hiapi.ai/v1/tasks \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-image",
"input": {
"prompt": "A cinematic product campaign with sharp text",
"aspect_ratio": "1:1"
}
}'The create request immediately returns a taskId; image generation continues asynchronously.
Low-cost Chinese-prompt generation, realistic portraits, signage, urban nights, and food assets.
1:1, 4:3, 3:4, 16:9, and 9:16.
The current public contract exposes only prompt and aspect_ratio. Do not add undeclared resolution or format fields.
No. The current Z-Image model ID is text-to-image only.
POST /v1/tasks with model: z-image and input.prompt. aspect_ratio is optional.
Start with the subject, environment, and visual goal, then add material, light, camera, and exact text.
Draft
4 steps
Final
8 steps
Choose one of five common aspect ratios and keep the request focused on the prompt.
Confirm the result in Playground, then reuse the same prompt and model ID in an asynchronous task.