--- title: LangSmith LLM Gateway enters public beta with spend... description: LangChain has launched LangSmith LLM Gateway in public beta. It acts as a middleware layer between AI agents and LLM providers, providing governance features... canonical: https://daily.dev/posts/langsmith-llm-gateway-enters-public-beta-with-spend-limits-rate-limiting-and-pii-redaction-taj5tsav7 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: LangSmith LLM Gateway enters public beta with spend limits, rate limiting, and PII redaction | daily.dev og:description: LangChain has launched LangSmith LLM Gateway in public beta. It acts as a middleware layer between AI agents and LLM providers, providing governance features... og:url: https://daily.dev/posts/langsmith-llm-gateway-enters-public-beta-with-spend-limits-rate-limiting-and-pii-redaction-taj5tsav7 og:image: https://api.daily.dev/og/posts/Taj5TsAv7.png og:image:alt: LangSmith LLM Gateway enters public beta with spend limits, rate limiting, and PII redaction og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # LangSmith LLM Gateway enters public beta with spend limits, rate limiting, and PII redaction **[Collections](https://daily.dev/sources/collections)** · 1 min read · 2 upvotes · 0 comments ## Summary LangChain has launched LangSmith LLM Gateway in public beta. It acts as a middleware layer between AI agents and LLM providers, providing governance features including spend and rate limits at org, workspace, user, or API key granularity, PII and secrets redaction before requests reach the model, and policy violation tracking as traceable events in LangSmith. Setup requires only a single base_url change. Planned features include tool call governance, MCP server controls, model fallbacks, and deeper security controls. ## Content LangChain has launched LangSmith LLM Gateway in public beta - a runtime governance layer that sits between AI agents and LLM providers. ## What it does The gateway handles a few things that previously required stitching together separate tools: - **Spend and rate limits** at the org, workspace, user, and API key level - including per-customer controls for apps with end users - **PII and secrets redaction** before requests reach the model - **Policy violations** surfaced as traceable events directly inside LangSmith - **Access to OSS models** like Kimi-K3 - **Coding agent integration** out of the box Setup is a base_url swap. That's it. ## Why it matters Runtime governance for agents has been awkward to implement - you'd typically bolt on a guardrails platform, wire up a separate audit pipeline, and hope the observability stack ties it all together. The gateway collapses that into one place, which is especially useful as agent deployments get more complex and the blast radius of a misconfigured spend limit grows. ## What's coming LangChain has flagged tool call governance, MCP server controls, model fallbacks, and deeper security controls as planned additions. ## Questions this post answers ### What does the LangSmith LLM Gateway do for AI agent deployments? It acts as a runtime governance layer sitting between AI agents and LLM providers, now in public beta. It provides spend and rate limits at the org, workspace, user, and API key level (including per-customer controls), PII and secrets redaction before requests reach the model, and policy violations surfaced as traceable events inside LangSmith. Setup only requires swapping the base_url. _Teams adding governance to agent deployments can follow gateway rollouts like this on daily.dev._ ### Does the LangSmith LLM Gateway support open source models? Yes, the public beta of LangSmith LLM Gateway includes access to OSS models such as Kimi-K3, alongside out-of-the-box coding agent integration. It's positioned as a single layer replacing the separate guardrails platforms, audit pipelines, and observability stacks teams previously had to wire together for runtime agent governance. _Anyone weighing OSS versus proprietary model access in agent stacks can track updates like this on daily.dev._ ### What features are planned next for LangSmith LLM Gateway after its public beta? LangChain has flagged tool call governance, MCP server controls, model fallbacks, and deeper security controls as planned additions beyond the current public beta feature set of spend limits, rate limiting, and PII redaction. _Following an evolving governance layer like this helps agent builders on daily.dev plan ahead for MCP controls._ --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain](https://daily.dev/tags/langchain) [View this post on daily.dev](https://daily.dev/posts/langsmith-llm-gateway-enters-public-beta-with-spend-limits-rate-limiting-and-pii-redaction-taj5tsav7) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"LangSmith LLM Gateway enters public beta with spend limits, rate limiting, and PII redaction","url":"https://daily.dev/posts/langsmith-llm-gateway-enters-public-beta-with-spend-limits-rate-limiting-and-pii-redaction-taj5tsav7","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/langsmith-llm-gateway-enters-public-beta-with-spend-limits-rate-limiting-and-pii-redaction-taj5tsav7"},"datePublished":"2026-07-30T18:07:10.460Z","dateModified":"2026-09-13T19:41:38.576Z","description":"LangChain has launched LangSmith LLM Gateway in public beta. It acts as a middleware layer between AI agents and LLM providers, providing governance features...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c33b39402425bd7da03e18177e227e21?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c33b39402425bd7da03e18177e227e21?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/langsmith-llm-gateway-enters-public-beta-with-spend-limits-rate-limiting-and-pii-redaction-taj5tsav7","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,langchain","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"LangSmith LLM Gateway enters public beta with spend limits, rate limiting, and PII redaction"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/langsmith-llm-gateway-enters-public-beta-with-spend-limits-rate-limiting-and-pii-redaction-taj5tsav7#faq","mainEntity":[{"@type":"Question","name":"What does the LangSmith LLM Gateway do for AI agent deployments?","acceptedAnswer":{"@type":"Answer","text":"It acts as a runtime governance layer sitting between AI agents and LLM providers, now in public beta. It provides spend and rate limits at the org, workspace, user, and API key level (including per-customer controls), PII and secrets redaction before requests reach the model, and policy violations surfaced as traceable events inside LangSmith. Setup only requires swapping the base_url. Teams adding governance to agent deployments can follow gateway rollouts like this on daily.dev."}},{"@type":"Question","name":"Does the LangSmith LLM Gateway support open source models?","acceptedAnswer":{"@type":"Answer","text":"Yes, the public beta of LangSmith LLM Gateway includes access to OSS models such as Kimi-K3, alongside out-of-the-box coding agent integration. It's positioned as a single layer replacing the separate guardrails platforms, audit pipelines, and observability stacks teams previously had to wire together for runtime agent governance. Anyone weighing OSS versus proprietary model access in agent stacks can track updates like this on daily.dev."}},{"@type":"Question","name":"What features are planned next for LangSmith LLM Gateway after its public beta?","acceptedAnswer":{"@type":"Answer","text":"LangChain has flagged tool call governance, MCP server controls, model fallbacks, and deeper security controls as planned additions beyond the current public beta feature set of spend limits, rate limiting, and PII redaction. Following an evolving governance layer like this helps agent builders on daily.dev plan ahead for MCP controls."}}]} ```