Does Bria-3.2-vector support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Bria-3.2-vector is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Bria-3.2-vector hosted?

Bria-3.2-vector runs on US hosting routes through the Opper gateway.

Is Bria-3.2-vector trained on prompts and outputs?

No. Every hosting route for Bria-3.2-vector is configured so customer prompts and outputs are not used to train models by default.

Bria-3.2-vector

by Bria

Bria-3.2-vector is a variant of Bria's commercial-ready text-to-image technology built for vector graphics generation. It produces scalable SVG output rather than raster images, making it suited to design workflows that need icons, logos, and flat illustrations that hold quality at any resolution. Built on the same 4-billion-parameter foundation as Bria-3.2, the vector variant is trained to understand the clean lines, flat colors, and geometric constraints of vector art. It supports controlled generation through parameters such as aspect ratio, text guidance scale, and diffusion steps, and its SVG output opens directly in tools like Illustrator, Figma, and Inkscape. The model trains exclusively on licensed data and carries commercial legal coverage for production use. It is available through API endpoints and design-platform integrations for rapid vector asset creation.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Pricing

$0.04 / generation

Billing

Per generation

US residency available
Zero data retention via Enterprise
No training by default

Pricing

Usage-based pricing, billed per generation, not by token.

Variant	Price
Standard	$0.04 / generation

Available routes

Bria-3.2-vector 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.

Data handling per route

Each route hosting Bria-3.2-vector has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Limited debug logs
Third-party access: None disclosed
GDPR DPA: No DPA
Transfer mechanism: unknown

Get started

Call Bria-3.2-vector 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.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "deepinfra/Bria/Bria-3.2-vector",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);

Compare Bria-3.2-vector with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Bria-3.2-vector vs DALL-E 3 Bria-3.2-vector vs Imagen 4 Bria-3.2-vector vs Seedream 4 Bria-3.2-vector vs fibo Bria-3.2-vector vs Bria-3.2 Build your own comparison

Other models from Bria