> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qingbo.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Z.ai Image

> Zhipu Z.ai image generation — lightweight and fast, bilingual prompts, low latency and low cost

Lightweight and fast image generation from Zhipu Z.ai, with strong support for both Chinese and English prompts. **Low latency, low price** — suited for high-frequency scenarios like batch sketches, operations creatives, and quick previews.

Per-image pricing. Pure text-to-image (no reference images), fixed at 1 image per call.

## Pricing

| Model           | Price (per image) |
| --------------- | ----------------- |
| `z-image-turbo` | `$0.010625`       |

## Examples

<CodeGroup>
  ```bash Text-to-image (minimal) theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "z-image-turbo",
      "prompt": "Seaside cafe at sunset, wooden deck, warm tones",
      "aspect_ratio": "16:9",
      "resolution": "1K"
    }'
  ```

  ```bash Enable smart rewrite theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "z-image-turbo",
      "prompt": "A Shiba Inu",
      "prompt_extend": true,
      "aspect_ratio": "1:1",
      "resolution": "2K"
    }'
  ```
</CodeGroup>

<ResponseExample>
  ```json Submission successful theme={"system"}
  {
    "task_id": "task-wave1775285160b950328499",
    "model": "z-image-turbo",
    "action": "generate",
    "status": "queued",
    "created_at": 1775285160040,
    "progress": 0
  }
  ```
</ResponseExample>

After submission, poll status with [`GET /v1/tasks/{task_id}`](/en/api-reference/task/status). See [Task System](/en/docs/task-system) for details.

## Available Models

| Model ID        | Description                                                                      |
| --------------- | -------------------------------------------------------------------------------- |
| `z-image-turbo` | Lightweight and fast, bilingual, 1K/2K, pure text-to-image (no reference images) |

## Common Parameters

<ParamField body="model" type="string" required>
  Choose one from the [Available Models](#available-models) list
</ParamField>

<ParamField body="action" type="string" default="generate">
  Operation type. `z-image-turbo` only supports `generate` (text-to-image)
</ParamField>

<ParamField body="prompt" type="string" required>
  Image description. Strong support for both Chinese and English. **Max 800 characters**
</ParamField>

<ParamField body="n" type="integer" default="1">
  Number of images. **This model is fixed at 1 image per call; `n > 1` is not supported**
</ParamField>

<ParamField body="seed" type="integer" default="-1">
  Random seed. `-1` for random; a fixed value reproduces similar results
</ParamField>

<ParamField body="aspect_ratio" type="string" default="1:1">
  Aspect ratio. Options:

  * `1:1` — Square
  * `4:3` / `3:4` — Standard landscape / portrait
  * `16:9` / `9:16` — Widescreen landscape / portrait
  * `3:2` / `2:3` — Camera ratio landscape / portrait
</ParamField>

<ParamField body="resolution" type="string" default="1K">
  Output resolution. Options: `1K` / `2K`
</ParamField>

<ParamField body="callback_url" type="string">
  Webhook callback URL, invoked when the task reaches a terminal state. See [Callback Mechanism](/en/docs/sync-async#async-task-webhook)
</ParamField>

<ParamField body="callback_events" type="string[]">
  Events to receive callbacks for. Defaults to terminal events only. See [Callback Mechanism](/en/docs/sync-async#async-task-webhook)
</ParamField>

## Model-Specific Parameters

<ParamField body="prompt_extend" type="boolean" default="false">
  Smart prompt rewrite. When enabled, AI auto-optimizes the prompt for better results, but **adds extra cost**
</ParamField>

## Notes

* **Single image per call** — `n` is fixed at 1; submit multiple tasks for multiple images
* **Prompt limit 800 characters** — trim long prompts yourself
* **Enabling `prompt_extend` increases cost** — AI rewrite consumes extra inference cost; enable selectively for batch scenarios
* **Pure text-to-image** — does not accept `image_urls` reference images; use other models for image-to-image

## Resource Limits

| Item              | Limit                       |
| ----------------- | --------------------------- |
| Images per call   | Fixed at 1                  |
| Prompt length     | ≤ 800 characters            |
| Output resolution | `1K` / `2K`                 |
| Output file       | JPG, URL valid for 24 hours |

## Related Docs

* [Task System](/en/docs/task-system) — Task state machine / polling cadence / async push
* [Request & Response](/en/docs/request-response) — Common error codes / Headers / rate limits
* [Authentication](/en/docs/authentication) — API Key application and usage