LFM2.5-2.6B (free)

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or knowledge-heavy tasks. Prompts and outputs may be retained and used to train Liquid models.

ChatLiquid66k tokensFree

liquid/lfm-2.5-2.6b:free

Context
66k tokens
Completion cap
8,192
Tools
Yes
JSON
Yes
Released
2026-08-11

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "liquid/lfm-2.5-2.6b:free",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is LFM2.5-2.6B (free)?
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or knowledge-heavy tasks. Prompts and outputs may be retained and used to train Liquid models. LFM2.5-2.6B (free) runs on the Geek Hub API (OpenAI-compatible). Model id: liquid/lfm-2.5-2.6b:free.
Is LFM2.5-2.6B (free) free?
Yes. The listed price is zero — you are not charged for prompt or completion tokens. Free endpoints are rate limited.
What is the context length of LFM2.5-2.6B (free)?
LFM2.5-2.6B (free) has a 66k tokens context window. It supports up to 8,192 completion tokens.
Does LFM2.5-2.6B (free) support tool calling and structured outputs?
LFM2.5-2.6B (free) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was LFM2.5-2.6B (free) released?
LFM2.5-2.6B (free) was released on 2026-08-11.