Liquid

Cambridge, United States · Founded 2023 · 11 employees · Computers Electronics and Technology

Our ultra-efficient multimodal models are turning the promise of an AI-powered world into reality. Optimized for CPUs, GPUs, and NPUs, they enable privacy-, low-latency, and security-critical applications everywhere, not just the cloud.

liquid.ai

1 Model

Model	Modality	Context	Input $/M	Output $/M
LiquidAI: LFM2-24B-A2B LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.	text→text	33K	$0.03	$0.12

LiquidAI: LFM2-24B-A2B

33K

In: $0.03/MOut: $0.12/Mtext