---
title: creative_generate_image
description: Start an image generation job in the connected workspace.
canonical_url: https://orchestor.io/docs/en/mcp/tools/creative/creative_generate_image
markdown_url: https://orchestor.io/docs/en/mcp/tools/creative/creative_generate_image.md
contentType: reference
---

# creative_generate_image

Start an image generation job in the connected workspace.

**Operation:** Write. Requires read-and-write OAuth consent.

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `body` | object | Yes | Image generation input. |
| `body.model` | string | Yes | Model ID from `creative_image_models_list`. |
| `body.prompt` | string | Yes | Describe the image to create or the change to make. |
| `body.mode` | string | No | Use `async` (the default) to receive a job immediately. |
| `body.image_urls` | array of strings | No | Public HTTPS URLs for reference images, if the model supports them. |
| `body.aspect_ratio` | string | No | Output aspect ratio supported by the model. |
| `idempotency_key` | string | Yes | Use a unique key per action. Reuse it to retry identical input. |
| `approval_receipt` | string | No | Receipt returned with the plan. Supply it after user confirmation. |

Generation calls an external provider and can consume Creative credits. The first call returns a plan. After confirmation, resubmit the same input with its `approval_receipt`. Save `data.job.id` and pass it to `creative_jobs_wait`. A retry with the same key and input returns the same job. Check `creative_image_models_get` for model pricing and supported inputs.

## Sample prompt

```text
Generate one square image of a blue ceramic vase on a white background.
```

[Creative](https://orchestor.io/docs/en/mcp/tools/creative.md) · [Tools](https://orchestor.io/docs/en/mcp/tools.md)

---

[Documentation index](https://orchestor.io/docs/llms.txt)
