Liquid Inference

Product Hunt Products
llm-routing inference api-gateway multi-model agentic-coding pricing

Summary

Liquid Inference 是一款 LLM 路由器，让多家模型提供商针对每次 prompt 动态竞价，从而为用户提供最低推理成本，兼容 Claude Code、Cursor 等主流 agentic 编码工具，支持数百个开源与闭源模型。

<p> LLM router where providers compete for every prompt </p> <p> <a href="https://www.producthunt.com/products/liquid-inference?utm_campaign=producthunt-atom-posts-feed&amp;utm_medium=rss-feed&amp;utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1272432?app_id=339">Link</a> </p>
Original Article
View Cached Full Text

Cached at: 10/08/26, 12:38 PM

# Liquid Inference: LLM router where providers compete for every prompt | Product Hunt Source: [https://www.producthunt.com/products/liquid-inference](https://www.producthunt.com/products/liquid-inference) \* Fully compatible with agentic coding tools: Claude Code, Codex, OpenCode, Cursor, Pi, Cline, and many more\. Full multi\-modal support\. \* Hundreds of open\- and closed\-weight models\. Create routing rule presets or use our Auto routing algorithms\. \* Providers compete dynamically on price for every prompt, offering the lowest marginal cost\. \* Sign up for free with email, first 500 users get $20 of free inference\. Receive 20% of referred fees as free inference, 10% for second\-level referrals\.

Similar Articles

LFM2.5-24B-A2B (7 minute read)

TLDR AI

Liquid AI 发布 LFM2.5-24B-A2B，一个 24B 参数、仅 2B 激活参数的开源权重推理模型，专为快速、私密的设备端智能体设计，在多个智能体与工具使用基准上超越更大的 MoE 模型。

BerriAI/litellm

GitHub Trending (daily)

LiteLLM 是一个开源 AI 网关，提供统一接口以 OpenAI 格式调用 100 多个 LLM 提供商，可作为 Python SDK 或自托管代理服务器使用，面向企业级部署。

@FakeMaidenMaker: MIT just open-sourced an inference library that lets large models read tens of millions of tokens at once—RLM from MIT CSAIL's OASYS lab, with involvement from DSPy and ColBERT author Omar Khattab, even VentureBeat covered it…

X AI KOLs Timeline

MIT open-sourced the RLM (Recursive Language Models) inference library, which handles ultra-long contexts by having the model recursively call itself programmatically, solving the limited context window problem of traditional models.

LiquidAI/LFM2.5-8B-A1B-GGUF

Hugging Face Models Trending

LiquidAI releases a GGUF quantized version of their LFM2.5-8B-A1B model, with instructions for use across multiple inference engines.