{"schema_version":"newruntime-agent-readable-v0.2","type":"post","stable_id":"post:langsmith-llm-gateway-runtime-controls","slug":"langsmith-llm-gateway-runtime-controls","title":"LangSmith LLM Gateway Puts Runtime Controls Between Agents and Models","description":"LangSmith LLM Gateway turns spend caps, rate limits, fallbacks, redaction, and provider routing into one governed layer for production agents.","retrieval_nugget":"LangSmith LLM Gateway turns spend caps, rate limits, fallbacks, redaction, and provider routing into one governed layer for production agents. LangChain made LangSmith LLM Gateway available in public beta. The release is not another model endpoint. It is a governance layer between production agents and the models they call.","status":"published","published_at":"2026-07-31","updated_at":"2026-07-31","record_date":"2026-07-31","date_kind":"published_at","topics":["agents","infrastructure","api-design","security"],"source_urls":["https://x.com/LangChain/status/2082879600137244978","https://x.com/LangChain/status/2082894996785488268","https://x.com/LangChain/status/2082897248443154887","https://www.langchain.com/blog/langsmith-llm-gateway-runtime-controls-for-production-agents"],"visuals":[{"id":"langsmith-llm-gateway-runtime-controls-nano-banana","kind":"editorial-diagram","role":"hero","src":"https://newruntime.com/images/posts/langsmith-llm-gateway-runtime-controls-nano-banana.webp","alt":"Hand-drawn systems diagram where production agents send model calls through a central gateway with spend limits, rate limits, fallback paths, redaction, and trace events.","caption":"LangSmith LLM Gateway moves model governance out of each agent and into one runtime layer before calls reach providers.","credit":"New Runtime synthesis from public source inspection","source_url":"https://www.langchain.com/blog/langsmith-llm-gateway-runtime-controls-for-production-agents","generated_with":"nano-banana-style-imagegen","width":1600,"height":900,"legend":[{"label":"Policy layer","description":"Spend caps, rate limits, and fallback rules are enforced before provider calls complete."},{"label":"Data protection","description":"Sensitive data can be redacted before it reaches model providers and LangSmith traces."},{"label":"Model choice","description":"The gateway supports provider keys, hosted open models, and compatible endpoints behind one interface."}]}],"telegram_message_id":2874,"telegram_url":"https://t.me/qwgai/2874","telegram_message_ids":[2874],"telegram_delivery_mode":"text_only","routes":{"html":"https://newruntime.com/posts/langsmith-llm-gateway-runtime-controls/","markdown":"https://newruntime.com/posts/langsmith-llm-gateway-runtime-controls.md","json":"https://newruntime.com/posts/langsmith-llm-gateway-runtime-controls.json"},"source_format":"markdown","next_reads":[{"type":"topic","path":"/topics/agents/","reason":"Explore the agents topic hub.","url":"https://newruntime.com/topics/agents/","title":"Agents - New Runtime","media_type":"text/html"},{"type":"topic","path":"/topics/api-design/","reason":"Explore the api design topic hub.","url":"https://newruntime.com/topics/api-design/","title":"API Design - New Runtime","media_type":"text/html"},{"type":"related_material","path":"/posts/vercel-passport-agent-identity-boundary/","reason":"Shares api design and infrastructure.","url":"https://newruntime.com/posts/vercel-passport-agent-identity-boundary/","title":"Vercel Passport Makes Identity a Deployment Boundary","media_type":"text/html"},{"type":"related_material","path":"/posts/vercel-sandbox-multi-user-agents/","reason":"Shares agents and infrastructure.","url":"https://newruntime.com/posts/vercel-sandbox-multi-user-agents/","title":"Vercel Sandbox Adds Unix Boundaries for Multi-Agent Work","media_type":"text/html"},{"type":"related_material","path":"/posts/vercel-agent-platform-control-plane/","reason":"Shares agents and api design.","url":"https://newruntime.com/posts/vercel-agent-platform-control-plane/","title":"Vercel's Agent Platform Surface Is Becoming a Control Plane","media_type":"text/html"}]}