Skip to content
Pydantic Docs

Google Gen AI

See every call your app makes to Google’s Gemini models through the Google Gen AI SDK (google-genai): the full conversation, how many tokens (the units a model reads and bills by, a few characters of text each) it used, how long it took, and any errors, as a trace (the full journey of one request, made of nested spans, where each span is one unit of work with a name, a start, and a duration) in Logfire.

What you’ll capture

  • Each model call as a span, with its duration and any exceptions
  • The full conversation between your app and the model
  • Response details, including the number of tokens used

Before you start

You’ll need a Logfire project. Open Add data in your project (top navigation) and follow the setup for your language: it signs your machine in with logfire auth (a browser sign-in, no token to copy) and, for production or other languages, creates a write token (the credential your app uses to send data). New to Logfire? Start with Getting Started.

You’ll also need a Google Gemini API key, from Google AI Studio. The Google Gen AI SDK reads it from the GEMINI_API_KEY (or GOOGLE_API_KEY) environment variable.

Installation

Install logfire with the google-genai extra:

Terminal
pip install 'logfire[google-genai]'

Usage

Add two lines to your app: logfire.configure() to connect to your project, and logfire.instrument_google_genai() to record every Gemini call.

By default, the prompts and completions are hidden: the spans show <elided> in their place. To capture the actual message content (so you can read the conversation in Logfire), set the OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT environment variable to true. This sends the prompt and response text to Logfire, so leave it off if that content is sensitive.

import os

from google.genai import Client

import logfire

# Set this to true to capture the actual prompts and completions in the spans.
os.environ['OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT'] = 'true'

logfire.configure()
logfire.instrument_google_genai()

client = Client()
response = client.models.generate_content(model='gemini-2.5-flash', contents=['Hi'])
print(response.text)
# Hello! How can I help you today?

This creates a span which shows the conversation in the Logfire UI:

Logfire Google Gen AI conversation

Verify it worked

Run your program, then open your project in the Logfire web app and go to the Live view. Within a few seconds you should see a span for the Gemini call. Click it to read the conversation and see the token count and duration.

Troubleshooting

Not seeing your model calls in Logfire? Check these first:

  • logfire.configure() runs before logfire.instrument_google_genai(). Configure the connection first, then instrument.
  • You called instrument_google_genai() exactly once.
  • Your Logfire write token is set. In local development, run logfire projects use <your-project>; in production, set the LOGFIRE_TOKEN environment variable. See Getting Started.
  • Prompts and completions show as <elided>? Set OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true before your app runs, as shown above.

Reference