Controlling AI Spend: How LangSmith Gateway Works
LangSmith has introduced a built-in LLM Gateway, a tool for managing AI agents at every stage of development and deployment. With Gateway, developers can set financial limits on LLM request spending, automatically strip personal data (PII) from prompts, and view full logs of all calls in real time. The integration is built directly into LangSmith, with no extra plugins or configuration.
AI-processed from LangChain Blog; edited by Hamidun News
LangChain's LangSmith has introduced LLM Gateway, a built-in tool for controlling spending on AI models, protecting user data and tracking every request in real time.
How can you control LLM spending without extra services?
LangSmith has built in LLM Gateway, which operates at the runtime level, at the moment a request executes, and controls spending on calls to OpenAI, Anthropic and other providers directly from the development environment.
How do you protect personal data in AI agents?
LLM Gateway lets you protect PII (users' personal data) and track every call in real time without additional infrastructure.
Is it possible to control spending on AI applications?
Yes. LangSmith Gateway lets developers control spending on calls to large language models, protect user data and track every call in real time, directly from the development environment.
How does PII protection work in LangSmith Gateway?
Gateway is built into LangSmith and works at the runtime level, sitting between the agent's code and the LLM provider's service (OpenAI, Anthropic and others) to protect users' personal data.
- Nov 1, 2026Local models lose to Opus and Codex: 0.21 on a MacBook versus 1.00 for Codex
- Nov 1, 2026Kimi scores 96.2% on a 1C database analytics test and emerges as a fallback if Claude access is blocked
- Nov 1, 2026OpenAI Rewrites GPT Behavior Rules: Five Values and a Chain of Command
- Nov 1, 2026Google admits AI Mode cuts search revenue, shares fall 15%
Key Questions Answered
How can you control LLM spending without extra services?
LangSmith has built in LLM Gateway, which operates at the runtime level, at the moment a request executes, and controls spending on calls to OpenAI, Anthropic and other providers directly from the development environment.
How do you protect personal data in AI agents?
LLM Gateway lets you protect PII (users' personal data) and track every call in real time without additional infrastructure.
Is it possible to control spending on AI applications?
Yes. LangSmith Gateway lets developers control spending on calls to large language models, protect user data and track every call in real time, directly from the development environment.
How does PII protection work in LangSmith Gateway?
Gateway is built into LangSmith and works at the runtime level, sitting between the agent's code and the LLM provider's service (OpenAI, Anthropic and others) to protect users' personal data.
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.