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.
liquid/lfm-2.5-2.6b
- Contexto
- 128k tokens
- Máx. completion
- 8,192
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2026-08-11
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
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"}]
}'Consigue tu API keyPreguntas frecuentes
- ¿Qué es 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 corre en el API de Geek Hub (compatible con OpenAI). Id: liquid/lfm-2.5-2.6b.
- ¿LFM2.5-2.6B es gratis?
- No. El input cuesta $0.3815 / 1M tokens y el output $0.545 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de LFM2.5-2.6B?
- LFM2.5-2.6B tiene una ventana de 128k tokens. Soporta hasta 8,192 tokens de completion.
- ¿LFM2.5-2.6B soporta tool calling y structured outputs?
- LFM2.5-2.6B acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó LFM2.5-2.6B?
- LFM2.5-2.6B se lanzó el 11 de agosto de 2026.
Más modelos de Liquid
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 ag
LFM2.5-24B-A2BLFM2.5-24B-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 ca