LangSmith LLM Gateway lets you enforce spend limits and redacts PII before requests reach the model. Not after the fact.

LangSmith LLM Gateway is a feature that enables proactive cost and privacy controls by enforcing spending limits and redacting personally identifiable information (PII) before API requests are sent to language models, rather than attempting to manage these concerns after model processing. This approach prevents unnecessary model invocations and associated costs while protecting sensitive data at the request layer.

Source: Harrison Chase (X) | 2026-05-29