LiquidAI models
LiquidAI publishes 2 models available on Zeplik. Pricing, context windows and capabilities below come straight from the live registry Zeplik routes and bills against.
All 2 LiquidAI models
LFM2.5-1.2B-Thinking (free)General purpose
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...
33K ctx0 cr/M outJanuary 2026
LFM2.5-1.2B-Instruct (free)General purpose
LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.
33K ctx0 cr/M outJanuary 2026
Pricing at a glance
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| LFM2.5-1.2B-Thinking (free) | 33K | 0 | 0 | January 2026 |
| LFM2.5-1.2B-Instruct (free) | 33K | 0 | 0 | January 2026 |