Designers and developers needing images that follow detailed references; free to try in Luma, with cheap per-image API pricing.

Kenning's take

What it does

Uni-1 is Luma's first model that both understands and generates images within one system, treating text and image tokens in a single sequence. It plans a picture before rendering it, and handles text-to-image, image editing and generation guided by up to nine reference images. It can be tried free in Luma's product and is sold to developers through the Luma Agents API.

• Text-to-image at 2048px
• Image editing and reference-guided generation
• Reasoning about scenes and spatial layout before rendering
• Culture-aware styles including memes and manga
• Higher-quality uni-1-max variant on the API

Who it suits. Designers, agencies and developers who need images that follow detailed directions and references.

Key facts

Category

AI models

Part of

Luma Dream Machine

Made by

Luma AI

Released

5 March 2026

How to get it

free to try in Luma's product; pay as you go or provisioned throughput on the Luma Agents API

Works on

Web, API

Free plan

Luma's Uni-1 page says it can be tried for free

API price

uni-1 pay as you go: $0.0404 per text-to-image image, $0.0434 per image edit (2048px); the Uni-1 product page lists token rates of $0.50 per million text input tokens and $3 per million text output tokens

Reviews and write-ups

• TestingCatalog 2026-03-06

FAQ

Facts from the maker's own pages and the sources listed. Checked 2026-10-11.