---
title: Why is my Vapi project still on the Langfuse v3 experience?
sidebarTitle: Vapi and the v4 upgrade
description: Projects ingesting via the Vapi integration stay on the Langfuse v3 experience until the integration is upgraded — what this means for dashboards, tables, and evaluators.
tags: [observability, integration]
---

# Vapi and the Langfuse v4 upgrade

Vapi sends data to Langfuse through the [Vapi integration](/integrations/no-code/vapi), 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](/docs/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 [#switch-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-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](/faq/all/llm-as-a-judge-migration). 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 while you wait for the Vapi integration upgrade. Once the integration is upgraded, follow the [evaluator upgrade guide](/faq/all/llm-as-a-judge-migration) to move to observation-level evaluators.

  Trace-level evaluators stop producing results for **all** projects at the
  Langfuse Cloud v4 cutover on November 16, 2026 (2026-11-16). We expect Vapi to complete
  its integration upgrade before then. Once Vapi has upgraded, you will be
  informed, and the only action you will have to take is to upgrade your
  evaluators before November 16, 2026 (2026-11-16); see the [evaluator upgrade
  guide](/faq/all/llm-as-a-judge-migration).

## Getting help

- **Questions on Langfuse v4**: Ask in the dedicated [GitHub Discussion](https://github.com/orgs/langfuse/discussions/12518)
- **Support**: Contact support@langfuse.com for enterprise customers

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/faq/all/partner-integration-v4-upgrade.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.