# GPT Image 2.5 Flare Edit

> Edit an existing image from a text instruction — it changes only what you ask for and leaves subject, composition and background intact, with optional masking and a second reference image for compositing.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/openai/gpt-image-2.5/flare/edit`
- **Model ID**: `openai/gpt-image-2.5/flare/edit`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: image-editing, photo-editing, inpainting, compositing, image-to-image, openai, gpt-image-2.5, flare

## Pricing

- **Price**: $0.0556 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/openai/gpt-image-2.5/flare/edit` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/openai/gpt-image-2.5/flare/edit/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/openai/gpt-image-2.5/flare/edit/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/openai/gpt-image-2.5/flare/edit/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`prompt`** (`string`, _required_):
  The edit instruction. Name the single change you want, then list what must stay the same — subject, layout, lighting, wording. Put any words you want rendered inside the image in quotes.

- **`mask_url`** (`string`, _optional_):
  Optional mask restricting the edit to one region. The mask should carry an alpha channel — transparent areas mark where changes are allowed — and match the reference image's size and format. Masking is prompt-guided, so the edited area may not follow the mask's shape exactly.

- **`image_size`** (`ImageSizeEnum`, _optional_):
  The aspect ratio and framing of the edited image. Match it to the source image's own aspect ratio unless you want the frame re-composed.
  - Default: `"landscape_4_3"`
  - Options: `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`

- **`image_urls`** (`array<string>`, _required_):
  One or two reference images. With one, the edit is applied to it; with two, elements from both can be combined into a single scene — address them in the prompt as 'image 1' and 'image 2'.

- **`num_images`** (`integer`, _optional_):
  How many edited images to generate from this request. Each image is charged as its own generation.
  - Default: `1`
  - Range: `1` to `4`

- **`output_format`** (`OutputFormatEnum`, _optional_):
  The file format of the edited image.
  - Default: `"png"`
  - Options: `"jpeg"`, `"png"`, `"webp"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "Change only the label wording to read \"NEROLI\"; keep the amber glass bottle, its cap, the pale marble surface, the lighting direction and the exact framing unchanged.",
  "image_size": "landscape_4_3",
  "image_urls": [
    "https://media.modelrunner.ai/RBnQU47YUtvzxzAk40HGq.png"
  ],
  "num_images": 1,
  "output_format": "png"
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/zeUwMyL6UwWxBc5jfMcsu.png"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/openai/gpt-image-2.5/flare/edit \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "Change only the label wording to read \"NEROLI\"; keep the amber glass bottle, its cap, the pale marble surface, the lighting direction and the exact framing unchanged.",
  "image_size": "landscape_4_3",
  "image_urls": [
    "https://media.modelrunner.ai/RBnQU47YUtvzxzAk40HGq.png"
  ],
  "num_images": 1,
  "output_format": "png"
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("openai/gpt-image-2.5/flare/edit", {
  input: {
  "prompt": "Change only the label wording to read \"NEROLI\"; keep the amber glass bottle, its cap, the pale marble surface, the lighting direction and the exact framing unchanged.",
  "image_size": "landscape_4_3",
  "image_urls": [
    "https://media.modelrunner.ai/RBnQU47YUtvzxzAk40HGq.png"
  ],
  "num_images": 1,
  "output_format": "png"
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "openai/gpt-image-2.5/flare/edit",
        arguments={
  "prompt": "Change only the label wording to read \"NEROLI\"; keep the amber glass bottle, its cap, the pale marble surface, the lighting direction and the exact framing unchanged.",
  "image_size": "landscape_4_3",
  "image_urls": [
    "https://media.modelrunner.ai/RBnQU47YUtvzxzAk40HGq.png"
  ],
  "num_images": 1,
  "output_format": "png"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/openai/gpt-image-2.5/flare/edit)
- [OpenAPI Schema](https://modelrunner.ai/models/openai/gpt-image-2.5/flare/edit/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/openai/gpt-image-2.5/flare/edit/llms.txt)