# GPT-1 | Image Edit

OpenAI Image Edit lets you modify images by removing, adding, or changing parts. It uses AI to fill in the selected area naturally.

## API Information

- **Model Slug:** openai-image-edit
- **Branded URL:** https://www.eachlabs.ai/openai/gpt-image/openai-image-edit
- **Provider:** OpenAI
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Input at $10 per 1M tokens, output at $40 per 1M tokens
- **Estimated Processing Time:** 25 seconds
- **Last Updated:** 2026-06-29
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/openai-image-edit

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Input at $10 per 1M tokens, output at $40 per 1M tokens

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Input at $10 per 1M tokens, output at $40 per 1M tokens |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | - |
| image_url_1 | string | Yes | - | - | - |
| mask_url | string | No | - | - | - |
| image_url_2 | string | No | - | - | - |
| image_url_3 | string | No | - | - | - |
| number_of_images | integer | No | 1 | 1–10 | - |
| quality | string | No | auto | auto,high,medium,low | - |
| background | string | No | auto | auto,transparent,opaque | - |
| image_size | string | No | auto | auto,1024x1024,1536x1024,1024x1536 | - |
| image_url_4 | string | No | - | - | - |
| image_url_5 | string | No | - | - | - |
| image_url_6 | string | No | - | - | - |
| image_url_7 | string | No | - | - | - |
| image_url_8 | string | No | - | - | - |
| image_url_9 | string | No | - | - | - |
| image_url_10 | string | No | - | - | - |
| image_url_11 | string | No | - | - | - |
| image_url_12 | string | No | - | - | - |
| image_url_13 | string | No | - | - | - |
| image_url_14 | string | No | - | - | - |
| image_url_15 | string | No | - | - | - |
| image_url_16 | string | No | - | - | - |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai-image-edit",
  "input": {
    "image_url_1": "https://storage.googleapis.com/magicpoint/inputs/input-image.png",
    "prompt": "a cyberpunk-themed, highly detailed and realistic portrait of the same woman from the input image, wearing a futuristic neon-lit jacket, glowing cybernetic implants on her face, short dyed blue hair, against a dark cityscape background with neon lights, same pose, looking at the camera, maintaining her natural facial features"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**openai-image-edit — Image Editing AI Model**

Developed by OpenAI as part of the **gpt-image** family, **openai-image-edit** empowers users to precisely modify existing images by masking areas and providing text prompts to add, remove, or change elements seamlessly. This **image-to-image AI model** solves the challenge of realistic photo editing without manual tools, delivering natural inpainting that blends edits into the original context. Ideal for developers seeking an **AI image editor API**, it transforms "edit images with AI" workflows by generating high-fidelity outputs from an input image and descriptive prompt.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.