Liquid AI's compact 1.7B agent model, post-trained for tool calling and structured outputs. 256K-token context with reasoning before it answers, sized for routing, extraction and cheap subagent loops where a small model is enough. Prompts and outputs may be retained to train Liquid's models.
▼LFM3 1.7B is somewhat expensive at $0.08/M tokens input and $0.20/M tokens output. Cached input reads are priced at $0.02/M tokens, making repeated context cheaper. The model supports extended reasoning, a 262K context window.