Tag
Analysis of why OpenRouter is valued at $7.5B: The core reason is that as an AI model proxy, all model-call spending passes through it with a 5.5% cut, while a comparable company that doesn't handle money, Portkey, was acquired for only $117M — a valuation gap of over 60x.
LangChain 于 Interrupt 大会举办 Agent Arena 活动，由 NVIDIA 赞助：参与者可通过玩俄罗斯方块训练智能体、用 LangSmith LLM Gateway 选择模型，并在排行榜上观看智能体对竞争霸。
An in-depth look at how magpie (a local LLM gateway maintained by yetone) achieves fully AI-driven development: it forms a nightly review loop through an AGENTS.md routing table and a LESSONS.md "mistake notebook," shipping 1204 releases in 19 days — compared with OpenClaw to illustrate its human-AI collaboration and acceptance mechanism.
A practitioner asks the community how to architect a production agent platform on AWS with ~20 agents and 50 MCP servers, weighing options like Bedrock AgentCore, Claude Agent SDK, Strands, LangGraph, A2A, LiteLLM, and Langfuse while demanding full Claude features and working prompt caching. The post seeks recommendations on framework choice, inter-agent communication, MCP hosting, and repo strategy.
Tavily 现已作为网络搜索引擎集成到 Merge Gateway 中，开发者只需在请求中添加 merge:web_search 并将 engine 设为 tavily，即可让模型在推理过程中获取带引用的实时搜索结果，无需单独的 Tavily 账号。
In an LLM Gateway benchmark pilot, Jev-based model routing achieved 33.2% cost savings versus a premium model, but a fixed mid-priced model offered better value with comparable task performance.
LangChain announces that SemIf, an open-source decision model, is available for free for one week in the LangSmith LLM Gateway, compatible with the TypeSafe SDK.
LangSmith LLM Gateway enables organizations to control model access by restricting API keys to specific models and automatically blocking unauthorized calls, demonstrated with Opus 5 and Sonnet 5.
The article examines the limitations of LLM gateways when agents can bypass them, suggesting that effective governance requires integrating egress enforcement and shadow detection to prevent unauthorized access.
The article highlights that most teams use separate tools for AI tracking and introduces Respan as a unified solution to route, observe, and evaluate LLM calls through a single gateway.
TanStack AI releases a first-party LLM Gateway adapter, enabling developers to access over 200 AI models from 40+ providers with a single API key and one-line model switching.
LangSmith's LLM Gateway now supports Kimi K3 and other open models via Gateway Credits, letting users call hosted models with just a LangSmith API key without configuring provider secrets.
LangSmith LLM Gateway is now in public beta, offering centralized governance for model calls in production agents — including spend caps, rate limits, model fallbacks, and per-customer policies to prevent outages and cost overruns.
Manifest explains why it deprecated its LLM router, arguing that model routing introduces unpredictability, breaks behavior consistency, and that prompt complexity cannot be inferred from the prompt alone, making caching and deliberate model selection more effective for most use cases.
LangChain 发布了一份概念指南，阐述了构建可控AI代理的框架，涵盖了认证、审计日志、速率限制、回退和集中化支出控制等系统级治理要素，并介绍了LLM网关作为运行时控制平面的作用。
OrcaRouter is a new AI gateway that intelligently routes prompts to the best model, offering cost savings, guardrails, and full observability with zero token markup and a free tier.
LLM Gateway Chat is a platform that provides access to multiple AI models for chat, image, video, and audio generation.
A detailed comparison of OpenRouter, Concentrate.ai, Portkey, and LiteLLM as LLM gateways for a B2B SaaS product, covering features, costs, and governance.
LangChain announces that LangSmith LLM Gateway can redact sensitive data like SSNs from requests before they reach LLM providers or logs, enhancing privacy and security.
Harbor v0.4.19 adds the ability to launch local agentic coding tools with local inference backends, integrating vllm, sglang, and llama.cpp, and includes a built-in LLM gateway for tool injection like web search.