Bria-3.2 is a rectified flow transformer text-to-image model with 4 billion parameters that generates images from natural language prompts. It delivers strong text rendering with a 70 percent OCR score, up from 5 percent in its predecessor, and achieves user preference scores around 65 percent higher than Bria-3.1. The model is roughly three times smaller than competing open-source text-to-image alternatives that typically run at 12 billion parameters, while delivering on-par quality to leading models. It supports multiple aspect ratios at around one million pixels of total resolution, runs efficiently with 30 to 50 inference steps, and fine-tunes about two times faster on professional GPUs such as the L40S and A100. Bria-3.2 trains exclusively on licensed data from leading content partners and includes commercial legal protections covering copyright and privacy claims. It is available via API, ComfyUI integration, or as source code and weights for commercial applications.
Usage-based pricing, billed per generation, not by token.
| Variant | Price |
|---|---|
| Standard | $0.04 / generation |
Bria-3.2 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 | Price |
|---|---|---|---|---|
| DeepInfra | US | Enterprise | No | $0.04 / generation |
Training posture across routes: No training on prompts by default.
Each route hosting Bria-3.2 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 Bria-3.2 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: "deepinfra/Bria/Bria-3.2",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
