LangSmith LLM Gateway — Self-Hosted Access Requests

LLM Gateway is a central governance layer that sits between your agents and the models they call. It gives teams one place to enforce runtime controls across agents, models, and providers, helping them consistently govern model usage while avoiding vendor lock-in.

Those controls include:

  • Spend limits at the organization, workspace, user, and API-key level
  • Reliability measures, including model fallbacks and rate limits‍‍
  • Data protection controls for PII and secrets (available in Enterprise plans via opt-in)

If you use LangSmith in a self-hosted environment and would like to participate in the LLM Gateway Public Beta, fill out this form and we will notify you once we’ve fulfilled your request.

Trusted by the best teams building agents