LFM2.5-2.6B is a compact reasoning model from Liquid AI.
Prices update automatically — checked daily against provider list prices.
Independent benchmark scores for LFM2.5-2.6B (free), measured by Artificial Analysis. Higher is better.
LFM2.5-2.6B (free) is an open-weight AI model by Liquid. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
LFM2.5-2.6B (free) is an AI language model from Liquid. It is open-weight: you can download it and run it on your own hardware, for free. It scores 11 on the Artificial Analysis intelligence index.
The weights are free and open — you can self-host LFM2.5-2.6B (free) and pay nothing per token. If you prefer a hosted API, list prices are Free per million input tokens and Free per million output tokens.
Independent benchmarks from Artificial Analysis give it GPQA 55.8%, Humanity's Last Exam 6.2%, Long Context Reasoning 5.3%, SciCode 14.2%, τ-Bench Banking 7.2%, Terminal-Bench 4.5%. It is particularly used for code generation.
Yes. LFM2.5-2.6B (free) has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.