Liquid
Models published by Liquid, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
Liquid d1 Ultra is Liquid AI's most capable decision model, returning calibrated probabilities instead of chat text. Send application state and typed questions and get answers in one call with zero generated tokens. It suits harder classification, routing and scoring decisions.
LFM 2.5 24B A2B is Liquid AI's open-weight reasoning mixture-of-experts model with 24B total and 2.45B active parameters. It always reasons before it answers and supports tool use and coding. It has a 131,072-token context window and uses the LFM Open License v1.0.
Liquid d1 is Liquid AI's first decision model, returning calibrated probabilities instead of chat text. Send application state and typed questions and get answers in one call with zero generated tokens. It suits classification, routing, scoring and moderation.
LFM 2.5 2.6B is Liquid AI's compact 2.6B-parameter chat model for general assistant and coding tasks. It allows up to 32,768 output tokens. It takes text in and streams text out.