Gemini 3 Pro Image Edit is the editing variant of Google’s Gemini 3 Pro Image model, also referred to by Google as Nano Banana Pro. Google describes it as a reasoning-driven image model for professional-grade image editing and generation with studio-quality precision and advanced creative control.
Google’s documentation and model pages say the model supports image and text inputs and outputs image and text, and that it is designed for complex, multi-turn image generation and editing.
| Developer | |
|---|---|
| Model ID | google/gemini-3-pro-image-edit |
| Release Date | February 22, 2026 |
| Modalities | Image, Text → Image |
Studio-quality editing
Google describes the model as offering studio-quality precision and advanced creative control for image generation and editing.
Multi-turn image workflows
The model is described as best for complex and multi-turn image generation and editing.
Text and image I/O
Google’s docs list supported data types as image and text for input and image and text for output.
Image editing support
The model supports image editing, including multi-turn image editing and interleaved images and text in Google’s enterprise documentation.
Thinking and search grounding
Google lists Thinking as supported and Search grounding as supported for the model.
Professional image editing
Google positions the model for precise edits to existing images, including localized refinements and complex transformations.
Image generation from prompts
The model supports image generation alongside editing, including text-to-image workflows.
Multi-reference visual composition
Third-party and model-card sources describe support for multi-input or reference-image workflows for combining visual context across images.
Text-heavy visuals
Google and the model card highlight strong text rendering, including text editing and infographics-related capabilities.
Gemini 3 Pro Image
Google’s model pages refer to Gemini 3 Pro Image as the underlying image model and Nano Banana Pro as its public-facing name.
Sources: https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image · https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-pro-image · https://deepmind.google/models/gemini-image/pro/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Edit images from text prompts, including making changes like relighting, season swaps, and object additions. It is also documented for conversational editing, where changes are requested in multiple turns while preserving visual context.
It is suited to complex graphic design tasks that need studio-quality precision and advanced creative control. It is also described as best for high-fidelity product mockups and factual data visualizations that require accurate text rendering.
import requests r = requests.post( "https://api.aimlapi.com/v1/images/generations", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "google/gemini-3-pro-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-3-pro-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-3-pro-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.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Gemini 3 Pro Image Edit This page | Image generation | |||
| Image generation at scale | ||||
| Image generation at scale |
Gemini 3 Pro Image Edit takes image, text as input and returns image.
Gemini 3 Pro Image Edit became available on February 23, 2026.
Yes, Gemini 3 Pro Image Edit accepts image input as well as a text prompt.
Gemini 3 Pro Image Edit was built by Google.
Send a request to https://api.aimlapi.com/v1/images/generations with google/gemini-3-pro-image-edit as the model id.
Yes. Gemini 3 Pro Image Edit is served through AI/ML API, so the same key and endpoint format used for other models applies.
It is an image generation model, specifically an image-to-image model that edits images based on text prompts.
