# GPT Image | v1.5 | Edit

GPT Image 1.5 creates highly detailed images with accurate prompt interpretation, maintaining consistent composition, realistic lighting, and refined visual detail.

## API Information

- **Model Slug:** gpt-image-v1-5-edit
- **Branded URL:** https://www.eachlabs.ai/openai/gpt-image/gpt-image-v1-5-edit
- **Provider:** OpenAI
- **Category:** Image to Image
- **Output Type:** array
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** gpt-image-1.5: text 5/10 per M + image 8/32 per M
- **Estimated Processing Time:** 60 seconds
- **Last Updated:** 2026-07-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/gpt-image-v1-5-edit

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** gpt-image-1.5: text 5/10 per M + image 8/32 per M

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | gpt-image-1.5: text 5/10 per M + image 8/32 per M |
| Default (fallback) | Fallback if token breakdown unavailable |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The prompt for image generation |
| image_urls | array | Yes | - | 1–10 | The URLs of the images to use as a reference for the generation. |
| image_size | string | No | 1024x1024 | 1024x1024,1536x1024,1024x1536 | Aspect ratio for the generated image |
| background | string | No | auto | auto,transparent,opaque | Background for the generated image |
| quality | string | No | high | low,medium,high | Quality for the generated image |
| input_fidelity | string | No | high | low,high | Input fidelity for the generated image |
| num_images | integer | No | 1 | 1–4 | Number of images to generate |
| moderation | string | No | low | low,auto | Content moderation level. low is less restrictive, auto is standard filtering. |
| output_format | string | No | png | jpeg,png,webp | Output format for the images |

## 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": "gpt-image-v1-5-edit",
  "input": {
    "prompt": "Same athlete, same cliff, same slackline.Same height, same danger, same focus.But now one hand holds a violin. Balanced on the line, playing the violin mid air.",
    "image_urls": [
      "https://storage.googleapis.com/magicpoint/inputs/gpt-image-v1-5-edit-input.png"
    ]
  }
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "array",
  "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

**gpt-image-v1.5-edit — Image Editing AI Model**

Developed by OpenAI as part of the gpt-image family, **gpt-image-v1.5-edit** is an advanced **image-to-image AI model** that enables precise natural-language edits on existing images, such as adding or removing objects, swapping backgrounds, and retouching details while preserving lighting, composition, and identity. This model stands out for its superior text rendering in dense or small formats, making it ideal for creating professional posters, infographics, and UI mockups directly from edited images. Developers and creators seeking an **AI image editor API** or **OpenAI image-to-image** capabilities will find gpt-image-v1.5-edit delivers reliable, high-fidelity results with fewer prompt revisions needed for accurate positioning and layout.

## 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.