Name: Gemini 3 Pro Image Edit API
Brand: Google

Overview

What Is Gemini 3 Pro Image Edit API?

Gemini 3 Pro Image Edit is Google's editing endpoint for Nano Banana Pro (Gemini 3 Pro Image), a higher-fidelity image model built on Gemini 3 Pro. Google released it as a follow-up to Nano Banana (Gemini 2.5 Flash Image), aimed at studio-quality image generation and editing.

The model accepts image and text input and produces image and text output, with support for multi-turn editing and interleaved images and text within the same conversation.

Technical Reference

Developer	Google
Model ID	google/gemini-3-pro-image-preview-edit
Input token limit	65,536
Output token limit	32,768
Modalities	Image, Text to Image, Text

What Gemini 3 Pro Image Edit Brings to the Table

Model identity
Gemini 3 Pro Image Edit runs on the same underlying model as Nano Banana Pro, applied to editing existing images rather than generating new ones from scratch.

Editing capabilities
Google's documentation lists support for image editing, multi-turn image editing, and interleaved images and text, along with thinking and search grounding.

Content provenance
Generated and edited outputs carry Content Credentials (C2PA), giving a verifiable record of how an image was created or modified.

Uptime and performance

Uptime (24h): 100%
Uptime (7d): 100%
Availability (24h): 100%
Error rate (24h): 0%

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Edit images from text prompts, including relighting, season swaps, background changes, and object additions. It also supports conversational, multi-turn editing, where changes are requested step by step while preserving visual context.

It is suited to complex graphic design tasks that call for precise control, high-fidelity product mockups, and data visualizations that require accurate text rendering.

How to use Gemini 3 Pro Image Edit API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to google/gemini-3-pro-image-preview-edit.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/images/generations",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "google/gemini-3-pro-image-preview-edit",
      "prompt": "Change the background to a sunset beach",
      "image_url": "https://example.com/your-image.png"
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-3-pro-image-preview-edit",
    "prompt": "Change the background to a sunset beach",
    "image_url": "https://example.com/your-image.png"
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/images/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3-pro-image-preview-edit","prompt":"Change the background to a sunset beach","image_url":"https://example.com/your-image.png"}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.