Uni-1

Luma AI

· uni-1

Multimodal Understanding

Production

Highest Quality

Luma AI's unified multimodal model. Luma AI provides advanced image, video and multimodal capabilities that can be accessed through the DreamCache Model Hub, subject to API availability.

Best use cases: Cross-modal reasoning, creative direction, unified generation

9.5

Quality

8

Speed

7

Cost Eff.

9

Brand Safety

9

Control

9

Adherence

Input cost

Provider pricing applies

Output cost

Provider pricing applies

Generation cost

Provider pricing applies

Max context / duration

1M tokens multimodal

Aspect ratios

Any

Resolutions

Up to 4K

Input types

Text, images, video, 3D

Output types

Text, images, video, 3D

API endpoint

api.lumalabs.ai/uni-1/v1

Commercial use

Allowed

Data retention

Per provider policy

Regions available

Global

API connected

Connected

Last updated

Release date

DreamCache

We make machines dream.

© 2026 DreamCache AI Ltd. All rights reserved.

The Creative Innovation OS

DreamCache AI is an independent platform. Third-party model, product and company names are trademarks of their respective owners. References to providers indicate existing or planned technical compatibility and do not imply endorsement, sponsorship or formal partnership. Model and integration availability may change according to API access, commercial terms and regional restrictions.