# GPT Image 2.6 Flare

OpenAI's everyday picture model: quick, with natural light and rich texture, and it changes only what you ask when it edits.

Model id: `gpt-image-2-6-flare`
Type: Image
Made by: OpenAI
Inputs: Text, References
Updated: Nov 4, 2026

## Pricing

| Setting | MiniAPI | fal | Difference |
| --- | ---: | ---: | ---: |
| low words only | $0.0148 / image | $0.0135 | +10% |
| low from references | $0.02 / image | $0.0182 | +10% |
| medium words only | $0.0269 / image | $0.0245 | +10% |
| high words only | $0.0314 / image | $0.0286 | +10% |
| medium from references | $0.0321 / image | $0.0292 | +10% |
| high from references | $0.0366 / image | $0.0333 | +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. |
| `markup_image_url` | No | https URL |  | Transparent PNG containing only annotations (circles, arrows, notes) that guide the edit of the first image. Must match the first image's dimensions. Cannot be combined with mask_url. Reference images are sent unmodified when set. Only with edit. |
| `mask_url` | No | https URL |  | A black and white picture: white is the part to change. Only with edit. |
| `image_urls` | For edit | https URLs |  | Pictures to use as references. Only with edit. |
| `background` | No | auto, transparent, opaque | auto | What to do with the background. |
| `quality` | No | auto, low, medium, high | high | Detail level. Higher costs more. |
| `num_images` | No | 1 to 10 | 1 | How many images to make. Each one is charged. |
| `output_format` | No | jpeg, png, webp | png | File type of the result. |
| `output_compression` | No | 0 to 100 |  | Compression level from 0 to 100. Only supported when output_format is 'jpeg' or 'webp'. |
| `frame_count` | No | 2 to 64 |  | GIF only: number of frames. image_size applies to each frame; reduce size or count if the request exceeds the pixel budget. |
| `frame_duration_ms` | No | 20 to 2000 |  | GIF only: milliseconds per frame, rounded to 10 ms. |
| `image_size` | No | square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto |  | 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. |
| `reasoning_effort` | No | low, medium, high, xhigh, max |  | How much reasoning the model spends before generating. Higher settings increase detail, latency, and token usage. |

## Quickstart

```bash
curl -X POST "https://api.minicut.ai/v1/queue/gpt-image-2-6-flare" \
  -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/gpt-image-2-6-flare/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/status",
  "response_url": "https://api.minicut.ai/v1/queue/gpt-image-2-6-flare/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "cancel_url": "https://api.minicut.ai/v1/queue/gpt-image-2-6-flare/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/cancel",
  "price": "0.031400",
  "currency": "USD"
}
```

Page: https://api.minicut.ai/models/gpt-image-2-6-flare
API reference: https://api.minicut.ai/docs/api