LFM2.5-24B-A2B
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks.
liquid/lfm-2.5-24b-a2b
- Context
- 128k tokens
- Completion cap
- 8,192
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-10-13
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-2.5-24b-a2b",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is LFM2.5-24B-A2B?
- LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks. LFM2.5-24B-A2B runs on the Geek Hub API (OpenAI-compatible). Model id: liquid/lfm-2.5-24b-a2b.
- Is LFM2.5-24B-A2B free?
- No. Input is $0.0545 per 1M tokens and output is $0.763 per 1M tokens on Geek Hub (markup included).
- What is the context length of LFM2.5-24B-A2B?
- LFM2.5-24B-A2B has a 128k tokens context window. It supports up to 8,192 completion tokens.
- Does LFM2.5-24B-A2B support tool calling and structured outputs?
- LFM2.5-24B-A2B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was LFM2.5-24B-A2B released?
- LFM2.5-24B-A2B was released on 2026-10-13.