Bria: Bria 3.2

Bria 3.2 is a compact text to image model built on fully licensed data. It delivers strong prompt alignment, high aesthetic quality, and reliable short text rendering. Ideal for enterprise workflows that need compliant image generation with predictable behavior and easy integration.

Compare models

bria-3-2

AvailableBriaImageSync

Price: From $0.04
Modalities: Image

About Bria 3.2

Bria 3.2 is a text-to-image model from Bria, trained only on licensed data and aimed at commercial image generation. It is a compact model with about 4 billion parameters, and Bria reports better aesthetics and much better rendering of short text than Bria 3.1. It takes a text prompt only; it does not edit or accept reference images.

Where it works well

Training data is fully licensed, which suits teams that must document where generated imagery comes from.
Short text inside images, around one to six words such as a sign or label, is the case Bria tuned for.
Bria reports a clear user-preference win over Bria 3.1 and a large gain in how accurately short text is rendered.
A compact model, so generations return quickly for batch catalogue and marketing work.

When to choose another model

Long sentences or dense paragraphs of text are outside what it was tuned for; pick a larger text-rendering model for posters.
It only generates from text, so editing an existing picture needs FIBO Edit or another editing model.
Its look is clean and commercial rather than highly stylised, which can feel plain for concept art.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to imageTokenLab endpoint

POST/v1/images/generations

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "text-to-image",
  "model": "bria-3-2",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to image

per image

Official price: $0.04
Verified price: —
Discount: —

	Official priceper image	Verified priceper image	Discount
Text to image	$0.04	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 17, 2026, 6:30 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Bria 3.2 in Console with a prompt ready to edit or send.

Help me create an image with bria-3-2 using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image

Marketing visuals
Produce campaign backgrounds, banners, and social images from a written brief, with the licensed-data provenance recorded for brand-safety review.
Product scenes
Place an imagined product in a lifestyle setting, such as a bottle on a kitchen counter, when you do not have a photo shoot.
Labels and signage
Generate storefronts, packaging mock-ups, or posters carrying a short word or slogan that must be spelled correctly.

Prompt examples

A wooden coffee shop storefront at dawn, hanging sign reading 'OPEN', warm light, shallow depth of field

Minimal flat-lay of skincare bottles on pale stone, soft window shadow, label text 'PURE'

Wide banner of a mountain lake in autumn, empty space on the left for headline copy

FAQ

What is Bria 3.2 used for?

It generates images from text for commercial work: ads, product scenes, web graphics, and mock-ups. Bria designed it around licensed training data and predictable output, so enterprises that review image provenance can use the results with fewer open questions.

Can Bria 3.2 write text inside images?

Yes, for short text. Bria says it is optimised for one to six words and reports a large gain in text accuracy over 3.1. Longer passages are less reliable, so review the output when a sentence must be exact.

Does Bria 3.2 edit existing images?

No. This model is text-to-image only. To change a picture you already have, use Bria FIBO Edit, which takes an image, an instruction and an optional mask.

How does Bria 3.2 differ from Bria FIBO?

Bria 3.2 is a smaller model driven by ordinary text prompts. FIBO is a larger model built around structured JSON prompts for fine control of lighting, camera and composition, and it also supports refinement of an existing result.

How much does Bria 3.2 cost?

On TokenLab, Bria 3.2 costs $0.04 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Bria 3.2 use?

Use https://api.tokenlab.sh/v1/images/generations for Bria 3.2. The request example below shows the matching code shape.

Which operations does Bria 3.2 support?

Bria 3.2 supports Text to image. Select an operation above to see its endpoint and request example.