Vapi and the Langfuse v4 upgrade
Vapi sends data to Langfuse through the Vapi integration, which the Vapi team operates. Projects relying on this integration are currently opted into the Langfuse v3 experience because the integration does not yet ingest data on the Langfuse v4 data model.
We are working with the Vapi team to upgrade the integration. As soon as the upgrade ships, affected projects see the v4 experience automatically — no action is needed on your side.
Switching to v4 early
You can opt into the v4 experience yourself at any time via the Langfuse v4 preview toggle (bottom-left in the UI). This gives you the significantly faster dashboards and tables of the v4 experience. You may opt-out again at any time.
Until the Vapi integration is upgraded, data ingested via Vapi appears in the v4 experience with a delay of approximately 15 minutes. If you need real-time data, keep the toggle off and switch after the integration upgrade.
Keep managing trace-level evaluators
Trace-level LLM-as-a-Judge evaluators are deprecated as part of Langfuse v4, and most projects should upgrade them to observation-level evaluators. Observation-level evaluators require the upgraded ingestion path, so for projects ingesting via Vapi this upgrade is currently blocked until the Vapi integration upgrade ships.
Continue creating and managing trace-level evaluators as before — they keep running throughout the transition. Once the integration is upgraded, follow the evaluator upgrade guide to move to observation-level evaluators.
Getting help
- Questions on Langfuse v4: Ask in the dedicated GitHub Discussion
- Support: Contact support@langfuse.com for enterprise customers
Last edited
