# Gemini 3 Pro | Image Edit

Gemine 3 Pro Edit transforms uploaded images through prompt based editing with smooth, accurate and high quality results

## API Information

- **Model Slug:** gemini-3-pro-image-preview-edit
- **Branded URL:** https://www.eachlabs.ai/google/gemini-3/gemini-3-pro-image-preview-edit
- **Provider:** Google
- **Category:** Image to Image
- **Output Type:** array
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.15 per image
- **Estimated Processing Time:** 0 seconds
- **Last Updated:** 2026-08-18
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/gemini-3-pro-image-preview-edit

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.15 per image
- **Pricing Details:** default: $0.15

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The prompt for image editing. |
| image_urls | array | Yes | - | 1–10 | The URLs of the images to use for image-to-image generation or image editing. |
| aspect_ratio | string | No | 1:1 | 21:9,16:9,3:2,4:3,5:4,1:1,4:5,3:4,2:3,9:16 | The aspect ratio of the generated image. |
| resolution | string | No | 1K | 1K,2K,4K | The resolution of the image to generate. |
| output_format | string | No | png | jpeg,png,webp | The format of the generated image. |
| num_images | integer | No | 1 | 1–4 | The number of images to generate. |

## 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": "gemini-3-pro-image-preview-edit",
  "input": {
    "prompt": "The cats are cuddiling each other",
    "image_urls": [
      "https://cdn-us.eachlabs.ai/defaults/35cab807014ee1f2b4a214ac4ffe7be0b12f8152b07ac95563e1017463346d4e.png",
      "https://cdn-us.eachlabs.ai/defaults/38fb5f3d09398512008e97690441798ba44b9303e0d4d155a31927640d0d7153.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

**gemini-3-pro-image-preview-edit — Image Editing AI Model**

gemini-3-pro-image-preview-edit, Google's advanced **image-to-image AI model** from the Gemini 3 family, enables precise editing of uploaded images using natural language prompts for smooth, high-quality transformations while preserving original composition. Known internally as part of Gemini 3 Pro Image Edit (Nano Banana Pro), this preview model excels in controlled modifications like object replacement, lighting adjustments, and background swaps, delivering professional-grade results up to 4K resolution. Developers and creators searching for a reliable **Google image-to-image** solution find it ideal for iterative workflows without regenerating entire visuals.

## 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.