# GPT Image | v2 | Edit

GPT Image 2 creates more advanced images with deeper prompt understanding, stronger compositional coherence, more realistic lighting, and richer fine-detail rendering.

## API Information

- **Model Slug:** gpt-image-v2-edit
- **Branded URL:** https://www.eachlabs.ai/openai/gpt-image/gpt-image-v2-edit
- **Provider:** OpenAI
- **Category:** Image to Image
- **Output Type:** array
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** gpt-image-2 edit: text in $5/M, image in $10/M, text out $40/M, image out $30/M. Note: gpt-image-2 always processes reference images at high fidelity, so input image tokens may be higher than other GPT image models.
- **Estimated Processing Time:** 60 seconds
- **Last Updated:** 2026-08-16
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/gpt-image-v2-edit

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** gpt-image-2 edit: text in $5/M, image in $10/M, text out $40/M, image out $30/M. Note: gpt-image-2 always processes reference images at high fidelity, so input image tokens may be higher than other GPT image models.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | gpt-image-2 edit: text in $5/M, image in $10/M, text out $40/M, image out $30/M. Note: gpt-image-2 always processes reference images at high fidelity, so input image tokens may be higher than other GPT image models. |
| Default (fallback) | Fallback if token breakdown unavailable (medium 1024x1024 equivalent) |

## Input Schema

No input parameters documented.

## 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-v2-edit",
  "input": {}
}'
```

## 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 | v2 | Edit Overview**

GPT Image | v2 | Edit, from OpenAI's GPT Image family, enables precise image-to-image transformations using natural language instructions, allowing users to modify existing images while preserving key details. This model solves the challenge of controlled editing in AI workflows, offering superior instruction-following compared to diffusion-based predecessors like DALL-E. Integrated natively into ChatGPT and the OpenAI API, it supports iterative refinement for professional applications such as design tweaks and content creation.

As part of the GPT Image series successor to DALL-E, GPT Image | v2 | Edit builds on GPT Image 1.5's foundation, emphasizing autoregressive architecture for advanced photorealism and edit precision. Developers access it via the **GPT Image | v2 | Edit API** or platforms like each::labs, streamlining **OpenAI image-to-image** tasks in automated pipelines. Its standout differentiator is maintaining image consistency during edits, generating results up to four times faster than prior versions.

## 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.