---
date: 2024-12-02
title: New documentation for Google Vertex AI and Gemini tracing
description: Comprehensive guides for tracing Google Vertex AI and Gemini models with Langfuse
author: Marc
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

We've published comprehensive documentation on how to trace Google Vertex AI and Gemini models with Langfuse. This guide helps you implement observability for your Google Vertex AI applications, including the Gemini model family.

## What's Included

1. **Step-by-step Integration Guide**: Detailed instructions for setting up Langfuse tracing with Google Vertex AI, including code examples and best practices.
2. **Framework Examples**: Ready-to-use code snippets demonstrating how to implement tracing for application frameworks such as LangChain.

## Key Tracing Features

- Automatic capture of prompts, completions, and tokens
- Latency tracking for model calls
- Cost calculation for Vertex AI usage
- Support for multi-modal inputs with Gemini
- Structured logging of model parameters and metadata

## How to Get Started

- [Google Vertex AI Documentation](/integrations/model-providers/google-vertex-ai)
- [Gemini Documentation](/integrations/model-providers/google-gemini)

<!-- 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/changelog/2024-12-02-tracing-docs-for-google-vertex-ai-and-gemini.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>.