数据状态

同步自 OpenRouter · 460 个模型 · source=openrouter · 2026-11-07T02:48:57.840Z

liquid

LFM3-1.7B

liquid/lfm-3-1.7b

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...

ToolsReasoning开源倾向text->text
上下文262k
输入 $/M$0.080
输出 $/M$0.200
智力指数—
代码指数—
Agent / Arena—
模型家族 · 历史版本 · 知识库

lfm-3

liquid · 知识库 168 模 / 36 族

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...

lfm-3 模型族。当前查看:LFM3-1.7B(版本 — · 1.7B)。下列历史版本由 OpenRouter 目录、本站网关上架与 Hugging Face 检索自动归并。

  • 参数量档位 1.7B
  • 归并版本 2 个
1.7B

历史版本 / 相关变体

版本模型参数来源说明
—当前LFM3-1.7B
liquid/lfm-3-1.7b
1.7BOpenRouter
—LFM3-1.7B (free)
liquid/lfm-3-1.7b:free
1.7BOpenRouter 免费/网关

定价与限制

输入$0.080 / 百万 tokens
输出$0.200 / 百万 tokens
缓存读 / 写$0.020 / —
最大输出8k
输入模态text
输出模态text
HFLiquidAI/LFM3-1.7B

支持参数

frequency_penaltyinclude_reasoninglogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

价格与基准分优先同步自 OpenRouter;网关短 ID 由本站平台清单补全,介绍/历史版本融合 Hugging Face 检索与家族知识库。能力验真请用 bench_v1 实验室 · OCR 天梯。

Guides & how to use this pageoptional

About

LFM3-1.7B: how to decide

LFM3-1.7B: live quotes and risk signals on GrokCode. Aggregation only — not a storefront.

Use related guides for methodology; use the tables above for numbers that change hourly.

FAQ

Where do LFM3-1.7B prices come from?
From public catalogs and lab snapshots. Prefer official pages for final billing truth.