AI provider

Luma AI

Luma AI develops models for images and video. Founded in 2021, the company is based in Redwood City, California. Its cofounders are CEO Amit Jain and CTO Alex Yu. Its current model families include Ray for video and Uni for images.

Explore models

Models & tools

Uni-1.1
Luma AI · Uni
Luma’s image generation and editing model, with a higher-quality Max tier and reference-image controls.
Launch date 11 May 2026API · Provider product
Ray2
Luma AI · Ray
A January 2025 video model designed for coherent motion, camera movement and ordered events.
Launch date 15 January 2025Deprecated API; check access detailsAPI
Ray2 Flash
Luma AI · Ray
A legacy Ray video model that can reframe supplied clips up to 30 seconds long.
Launch date not confirmedDeprecated API; check access detailsAPI
Ray3
Luma AI · Ray
A video model that introduced Luma's HDR workflow with 10-, 12- and 16-bit output options.
Launch date not confirmedDeprecated API; check access detailsAPI · Provider product
Ray3.14
Luma AI · Ray
An earlier Ray video model with native 1080p output and an 18-second Modify workflow.
Launch date not confirmedProvider product
Ray3.2
Luma AI · Ray
A video model for generation, editing, extension and reframing from text, image anchors or existing video.
Launch date not confirmedPreviewAPI · Provider product