Reve Image comes from Reve, an AI startup whose debut model launched in March 2025 after circulating in preview under the codename Halfmoon, and it quickly claimed the top position on the Artificial Analysis image arena. The model was trained from the ground up to excel at three things, following prompts faithfully, producing refined aesthetics, and rendering accurate text. Beyond text-to-image generation it supports instruction-based image editing and remixing from reference images, giving one model coverage of the full create-and-revise loop. It suits marketing and product visuals that need legible typography, scenes with multiple precisely specified elements, and workflows where the output has to match the brief on the first pass.
Reve Image 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 |
|---|---|---|---|---|---|
| US | Enterprise | No | — | — |
Each route hosting Reve Image 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; unknown.
Call Reve Image 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 a coding agent like Claude Code, Cursor or Codex 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: "reve/reve-image",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
