---
id: "liquid/lfm-2.5-2.6b"
also: ["liquid/lfm-2.5-2.6b-20260811", "LiquidAI/LFM2.5-2.6B"]
card_usd_per_m: "0.35 in, 0.5 out, at liquid/fp8"
cheapest_list_usd_per_m: "0.35 in, 0.5 out, at liquid/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.3496 in, 0.4999 out, at liquid/fp8 on openrouter"
context: 128000
max_output: 8192
input: ["text"]
output: ["text"]
released: "2026-08-11"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logprobs", "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 0
trains: 1
retains_prompts: 1
coding: 7.7000
---
# LiquidAI: 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...