Referencev1.0.0 Stable

Z Image Turbo API

Integrate high-performance AI image generation capabilities. This documentation provides complete API reference, integration guides, and code examples to help developers quickly build AI image applications.

https://zimageturbo.ai

Quick Start

Complete your first API call in just two steps: submit a generation task, then poll for status.

Submit Task

Send a POST request to the generate endpoint to get a Task ID.

Query Status

Use the Task ID to check progress until you get the image URL.

Authentication

Note: Please keep your API Key secure and do not expose it in client-side code.

HTTP Header

Authorization: Bearer {YOUR_API_KEY}

POST

https://zimageturbo.ai/api/generate

Create a new image generation task. This endpoint is asynchronous and returns a task_id plus initial status; call /api/status to retrieve the final images.

This endpoint responds immediately with task_id. Poll /api/status until the status becomes SUCCESS to obtain image URLs.

Body Parameters

Parameter Name	Type	Required	Description
`prompt`	string	Yes	Text prompt for generation (max 1000 characters).
`aspect_ratio`	string	Yes	Aspect ratio for the generated image. Allowed values: 1:1, 4:3, 3:4, 16:9, 9:16.

Response (JSON)

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "task_1234567890",
    "status": "IN_PROGRESS"
  }
}

GET

https://zimageturbo.ai/api/status

Query the execution status and results of a task.

Query Parameters

Parameter Name	Required	Description
`task_id`	Yes	The ID returned when submitting the task.

Response Example

{
  "code": 200,
  "message": "success",
  "data": {
    "status": "SUCCESS",
    "task_id": "xxxxxxxx",
    "request": {
      "prompt": "A beautiful sunset over mountains",
      "aspect_ratio": "16:9"
    },
    "response": [
      "https://cdn.example.com/images/task_xxx_0.jpeg"
    ],
    "consumed_credits": 15,
    "created_at": "2025-12-05 13:05:09",
    "error_message": null
  }
}

Billing

Cost per generation

$0.02 / request

Failed tasks are not charged.

Error Handling

401 UnauthorizedInvalid API Key
402 Payment RequiredInsufficient balance
429 Too Many RequestsRate limit triggered

About Z Image Turbo

Z Image Turbo is a generation engine optimized based on the latest diffusion models. It focuses on increasing inference speed to 300% of traditional models while maintaining extremely high fidelity. Suitable for real-time interaction, game asset generation, and e-commerce design scenarios.

Z-Image-Turbo — 6B-parameter, ultra-fast text-to-image

Z-Image-Turbo is a 6B-parameter text-to-image model from Tongyi-MAI, engineered for production workloads where latency and throughput really matter. It uses only 8 sampling steps to render a full image, achieving sub-second latency on data-center GPUs and running comfortably on many 16 GB VRAM consumer cards.

Ultra-fast generation with production-ready quality

Where many diffusion models need dozens of steps, Z-Image-Turbo is aggressively optimised around an 8-step sampler. That keeps inference extremely fast while still delivering photorealistic images and reliable on-image text, making it a strong fit for interactive products, dashboards, and large-scale backends—not just offline batch jobs.

Why it looks so good?

Photorealistic output at speed — Generates high-fidelity, realistic images that work for product photos, hero banners, and UI visuals without multi-second waits.
Bilingual prompts and text — Understands prompts in English and Chinese, and can render multilingual text directly in the image—helpful for cross-market campaigns, posters, and screenshots.
Low-latency, low-step design — Only 8 function evaluations per image deliver extremely low latency, ideal for chatbots, configuration tools, design assistants, and any “click → image” experience.
Friendly VRAM footprint — Runs well in 16 GB VRAM environments, reducing hardware costs and making local or edge deployments more realistic.
Scales for bulk generation — Its efficiency makes large jobs—catalogues, continuous feed images, or auto-generated thumbnails—practical without blowing up compute budgets.
Reproducible generations — A controllable seed parameter lets you recreate a previous image or generate small, controlled variations for brand safety and experimentation.

How to use

promptprompt – natural-language description of the scene, style, and any on-image text (English or Chinese).
sizesize (width / height) – choose the output resolution; supports square and rectangular images up to high resolutions (for example, 1536 × 1536).
seedseed – set to -1 for random results, or use a fixed integer to make outputs reproducible.

Z-Image-Edit Prompts