Name: Gemini 2.5 Flash Image Edit API
Brand: Google

Overview

What Is Gemini 2.5 Flash Image Edit API?

Gemini 2.5 Flash Image Edit is Google’s image generation and editing model for conversational, low-latency creative workflows. Google describes Gemini 2.5 Flash Image, also known as Nano Banana, as best for high-volume generation, conversational image editing, and native multimodal understanding.

The model supports image and text inputs and returns image and text outputs, and Google lists image generation as supported for this model.

Technical Reference

Developer	Google
Model ID	google/gemini-2.5-flash-image-edit
Release Date	February 22, 2026
Modalities	Image, Text → Image

What Gemini 2.5 Flash Image Edit Brings to the Table

Conversational editing
Google says the model supports natural-language image edits, including precise local changes such as blur, object removal, pose changes, and recoloring.

Multi-image fusion
The model can understand and merge multiple input images into a single result, enabling composition and style-transfer workflows.

Character and style consistency
Google says it can maintain the same subject or visual style across multiple generations for richer storytelling and repeated-use assets.

Supported data types
Google’s model page lists images and text as inputs, and images and text as outputs.

Platform support
Google documents Gemini 2.5 Flash Image as available in Vertex AI and Gemini-related developer documentation for image editing.

Where Gemini 2.5 Flash Image Edit Makes the Most Sense

Product and marketing visuals
Google gives examples such as combining multiple reference images into a single marketing, training, or advertising visual.

Photo cleanup and retouching
The model is described as useful for removing people or objects, fixing small details, and other targeted edits through natural-language prompts.

Iterative creative workflows
Google and its docs describe multi-turn or conversational editing, where users refine an image over multiple prompt turns.

Composited scene creation
Google says users can put objects into scenes, restyle rooms, and fuse images with a single prompt.

Gemini 2.5 Flash Image Edit vs the Alternatives

Gemini 3.1 Flash Image Preview
Google’s Vertex AI documentation lists this model as another image-editing option alongside Gemini 2.5 Flash Image.

Gemini 3 Pro Image Preview
Google’s Vertex AI documentation also lists this model as supporting image editing.

Sources: https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image · https://cloud.google.com/blog/products/ai-machine-learning/gemini-2-5-flash-image-on-vertex-ai · https://developers.googleblog.com/introducing-gemini-2-5-flash-image/

Uptime and performance

Uptime (24h): 100%
Uptime (7d): 100%
Availability (24h): 100%
Error rate (24h): 0%
End-to-end latency (24h median): 9.4s

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

Use cases

Gemini 2.5 Flash Image Edit is documented for conversational image editing, including targeted transformations and precise local edits such as removing a person from a photo, fixing a stain, changing colors, or altering a subject’s pose. It is also suited to multi-image composition and style transfer, where multiple reference images are combined into a single new image. Another documented use is maintaining character and style consistency across multiple generations, such as placing the same subject or product in different scenes without losing identity. It is also described as useful for high-volume generation and low-latency creative workflows that require native multimodal understanding.

How to use Gemini 2.5 Flash Image Edit API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to google/gemini-2.5-flash-image-edit.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/images/generations",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "google/gemini-2.5-flash-image-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-2.5-flash-image-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-2.5-flash-image-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.