ngrok AI Gateway adds Liquid AI and 160+ LLM API models; tiny LFM3-1.7B pages for a thirsty plant
JosephJacks_ · x · 2026-11-10
ngrok added two providers to its AI Gateway: Liquid AI's small models and LLM API's 160+ models, 100 of which run on ngrok credits — including Amazon Nova Pro, Llama 3.3 70B, Mistral Large 3, and voices from ElevenLabs, Cartesia, and Deepgram.
Liquid's lineup includes text models lfm3-1.7b ($0.08/$0.20 per 1M tokens) and lfm2.5-24b-a2b, vision model lfm3-vl-2b, audio models lfm3-audio-2b/omni-2b, and d1 decision models that return typed answers with probabilities.
In a playful test, every model correctly said WAKE for a downed production database, but for a thirsty office plant alert most chose SNOOZE — except LFM3-1.7B, which said WAKE six times out of seven.
More from Infra
- 26 researchers publish 212-page paper on feasibility of a "hardwired pause" of frontier AI — DavidSKrueger · 2026-11-10
- Frontier lab compute shifts hard: pre-training falls from 67% to 7%, post-training/RL now 55% — akbirthko · 2026-11-10
- Study of 1,600 Data Centers Finds Each Adds ~1,000-1,300 Local Jobs Within 3-5 Years — RachelVT42 · 2026-11-10
- rakyll teases Agent Substrate as 'agentic compute fabric' ahead of KubeCon keynote — rakyll · 2026-11-10
- Together Compiler hits 2.7x throughput gains on Kimi K3 at same per-user speed — togethercompute · 2026-11-10
- ThumbFree: open-source offline voice typing with on-phone Parakeet, sub-second latency — Affectionate-Top7058 · 2026-11-10