LFM2.5-2.6B

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.

ChatLiquid128k tokens$0.3815 / $0.545 · 1M

liquid/lfm-2.5-2.6b

Context
128k 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",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is LFM2.5-2.6B?
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 runs on the Geek Hub API (OpenAI-compatible). Model id: liquid/lfm-2.5-2.6b.
Is LFM2.5-2.6B free?
No. Input is $0.3815 per 1M tokens and output is $0.545 per 1M tokens on Geek Hub (markup included).
What is the context length of LFM2.5-2.6B?
LFM2.5-2.6B has a 128k tokens context window. It supports up to 8,192 completion tokens.
Does LFM2.5-2.6B support tool calling and structured outputs?
LFM2.5-2.6B 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 released?
LFM2.5-2.6B was released on 2026-08-11.

More models from Liquid