LangSmith now gives you a unified view of costs across your full agent workflow, not just LLM calls.

Submit custom cost metadata for any run, whether that's an expensive tool call, a third-party API, a retrieval step, or anything else your agent depends on. Everything rolls up into a single view so you can monitor, debug, and optimize spend across your entire stack.

Getting started Check out the documentation to start submitting custom cost metadata for your runs.