Gemini 3 Pro Image Preview, also known as Nano Banana Pro, combines Google's advanced reasoning with professional-grade image generation and editing. It is built for complex, multi-turn image creation that needs accurate text rendering, real-world grounding through Google Search, and high-fidelity detail, making it a fit for graphic design, product mockups, and data visualizations. With a 66K context window and up to 33K output tokens, the model is built to understand intricate visual briefs and refine images iteratively through conversational guidance. It offers studio-quality precision and detailed editing control, including consistent multi-image blending and identity preservation across multiple subjects. It best fits professional workflows where image generation demands reasoning-driven accuracy alongside creative sophistication.
Gemini 3 Pro Image Preview runs on 2 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Gemini | US | Enterprise | No | $2.00 | $12.00 |
| Google Cloud | US | Enterprise | No | $2.00 | $12.00 |
Training posture across routes: No training on prompts by default.
Each route hosting Gemini 3 Pro Image Preview has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Call Gemini 3 Pro Image Preview through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "gemini/gemini-3-pro-image-preview",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
