LiquidAI: LFM2.5-1.2B-Thinking (free)

LiquidAI LFM2.5-1.2B-Thinking is a text-in, text-out model from Liquid AI with a 32,768-token context window. It supports tool use and reasoning, which means it can handle multi-step tasks and external function calls, though structured output support is unconfirmed. With no maximum completion token ceiling listed, output length behavior is worth testing directly before committing to it for production workflows. The clearest reason to shortlist this model is cost: it is currently free, with no input or output charges. That makes it worth evaluating for low-stakes or high-volume use cases where budget is a constraint. The honest caveat is that there is no independent benchmark coverage to consult, so quality relative to other small reasoning models is unproven. Teams needing verified performance data before deployment should treat this as an experimental option and run their own task-specific evaluations first.