Antigravity Preview is a Google agentic model built for autonomous reasoning and multi-step task execution. It combines text and vision understanding with tool use and structured output, so it can drive workflows that decompose a goal into actions and coordinate function calls along the way. The model is geared toward applications that plan, act, and verify across several steps rather than answering a single prompt. It maintains context across extended interactions and can carry intermediate state through longer agentic sessions, with a 128k context window for substantial documents and history.
Antigravity Agent Preview runs on 1 route 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 |
Training posture across routes: No training on prompts by default.
Each route hosting Antigravity Agent 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.
Call Antigravity Agent 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/antigravity-preview-05-2026",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
