# Ideogram 4.5

Ideogram. Edits the picture you hand it and takes up to four more as references.

Model id: `ideogram-4.5`
Type: Image
Made by: Ideogram
Inputs: Text, First frame, References
Updated: Oct 29, 2026

## Pricing

| Setting | MiniAPI | fal | Difference |
| --- | ---: | ---: | ---: |
| very_low from references | $0.0088 image | $0.008 | +10% |
| low | $0.033 / image | $0.03 | +10% |
| medium | $0.066 / image | $0.06 | +10% |
| very_low words only | $0.066 image | $0.06 | +10% |
| very_low from a frame | $0.066 image | $0.06 | +10% |
| high | $0.242 / image | $0.22 | +10% |

You are not charged for a job that fails.

## Parameters

| Name | Required | Values | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` | Yes | text |  | What to make, in plain words. |
| `image_url` | For edit | https URL |  | A picture to start from. We fetch it and keep a copy for the job. Only with edit. |
| `mask_url` | No | https URL |  | A black and white picture: white is the part to change. Only with edit. |
| `reference_image_urls` | No | https URLs |  | Pictures that show a face, an outfit or a product to keep the same. Only with edit. |
| `quality` | No | low, medium, high, very_low | medium | Detail level. Higher costs more. |
| `enable_prompt_expansion` | No | true, false | true | Let the model add detail to a short prompt. Only with v4.5. |
| `num_images` | No | 1 to 8 | 1 | How many images to make. Each one is charged. |
| `context_window` | No | none, auto | none | Region to edit with high edit_precision. none edits the whole image, downscaled to at most 4194304 pixels. auto requires mask_url and fits the region around the mask; an oversized mask falls back to whole-image editing. Set context_window_box instead to pick the region yourself. Localized edits preserve the original image resolution and every pixel outside the region. Only with edit. |
| `context_window_box` | No |  |  | Explicit region to edit with high edit_precision, in source pixels with exclusive x_max/y_max. Must lie inside the image, measure at least 256 pixels per side, cover at most 4194304 pixels, and have an aspect ratio within 1:6 and 6:1. A mask may select only pixels inside it. Cannot be combined with context_window auto. Leave unset to edit the whole image. Only with edit. |
| `image_size` | No | square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9 |  | Width and height in pixels, or a named size. |
| `image_size.height` | No | to 14142 |  | The height of the generated image. |
| `image_size.width` | No | to 14142 |  | The width of the generated image. |
| `seed` | No | integer |  | The same seed with the same settings gives a similar result. Leave it out for a random one. |
| `context_window_box.x_max` | No | 0 to |  | Right edge in source pixels (exclusive). Only with edit. |
| `context_window_box.x_min` | No | 0 to |  | Left edge in source pixels (inclusive). Only with edit. |
| `context_window_box.y_max` | No | 0 to |  | Bottom edge in source pixels (exclusive). Only with edit. |
| `context_window_box.y_min` | No | 0 to |  | Top edge in source pixels (inclusive). Only with edit. |
| `edit_precision` | No | regular, high |  | regular uses Generate; high uses Precise Edit with unchanged-pixel restoration. Both always prepare structured edit instructions. Only with edit. |

## Quickstart

```bash
curl -X POST "https://api.minicut.ai/v1/queue/ideogram-4.5" \
  -H "Authorization: Key $MINIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red fox in fresh snow, morning light"}'
```

```json
{
  "request_id": "0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "status": "IN_QUEUE",
  "queue_position": 0,
  "status_url": "https://api.minicut.ai/v1/queue/ideogram-4.5/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/status",
  "response_url": "https://api.minicut.ai/v1/queue/ideogram-4.5/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "cancel_url": "https://api.minicut.ai/v1/queue/ideogram-4.5/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/cancel",
  "price": "0.066000",
  "currency": "USD"
}
```

Page: https://api.minicut.ai/models/ideogram-4.5
API reference: https://api.minicut.ai/docs/api