FIBO is an 8-billion-parameter, DiT-based, flow-matching text-to-image model trained exclusively on licensed data and on long, structured JSON captions of up to roughly 1,000 words. It uses SmolLM3-3B as its text encoder with a novel DimFusion conditioning architecture, enabling deterministic generation where identical inputs produce identical outputs. The model operates in three modes: Generate converts short prompts into detailed JSON specifications covering lighting, composition, and camera settings before rendering, Refine enables targeted attribute changes without cumulative generation drift, and Inspire extracts structured prompts from reference images for variation. TeaCache optimization speeds up inference by about three times with minimal quality loss. Marketed by Bria as the first deterministic visual foundation model, FIBO trains exclusively on rights-cleared data from over 20 premium content partners including Getty Images and Envato, and ships with full enterprise indemnification. It offers integration options across major design ecosystems including Adobe, Figma, and AWS.
Usage-based pricing, billed per generation, not by token.
| Variant | Price |
|---|---|
| Standard | $0.04 / generation |
fibo 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 fibo 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 fibo 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/fibo",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
