Google Gemini

Automatically capture all Gemini model calls made through the google-genai SDK.

Install

Python

pip install traceroot google-genai

Set up

Python

import traceroot
from traceroot import Integration

traceroot.initialize(integrations=[Integration.GOOGLE_GENAI])

Usage

Once initialized, all Gemini calls are captured automatically — including tool-call requests:

import os
from google import genai
from google.genai import types

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

weather_tool = types.Tool(function_declarations=[
    types.FunctionDeclaration(
        name="get_weather",
        description="Get current weather for a city",
        parameters=types.Schema(
            type="OBJECT",
            properties={"city": types.Schema(type="STRING", description="City name")},
            required=["city"],
        ),
    )
])

# This call is automatically traced
response = client.models.generate_content(
    model="gemini-3.8-flash",
    contents="What's the weather in Tokyo?",
    config=types.GenerateContentConfig(tools=[weather_tool]),
)

# The model asks to call get_weather; run it and send the result back yourself
print(response.function_calls)

Verify

Run your code and confirm the trace arrives:

In the TraceRoot UI: Navigate to Tracing > Traces in TraceRoot Cloud. You should see a trace with root span GenerateContent (or GenerateContentStream when streaming).
Via the CLI: Run traceroot traces list to inspect your recent traces from the terminal.

What gets captured

Attribute	Description
Model	`gemini-3.8-flash`, `gemini-3.5-flash-lite`, `gemini-3.1-pro-preview`, etc.
Contents	Input messages
Response	Generated text and function calls
Tokens	Input and output token counts
Cost	Calculated when the model ID matches TraceRoot’s pricing table
Latency	Request duration

Limitations

When passing Python functions as tools, the SDK’s automatic function calling executes the entire tool loop inside a single generate_content call, which produces one span priced on the final model call only. For accurate per-step spans and cost, pass function declarations or set automatic_function_calling=types.AutomaticFunctionCallingConfig(disable=True) and run the loop manually.

Run the example

Clone the repo and run a complete agent end-to-end.

Python

Run the Python example

Next steps

Python SDK Reference

Explore the full Python SDK reference and instrumentation options.

Cost Tracking

Learn how TraceRoot calculates token costs and tracks model spend.

Overview

Native

Frameworks

Model Providers

Internal Model Providers

Install

Set up

Usage

Verify

What gets captured

Limitations

Run the example

Python

Next steps

Python SDK Reference

Cost Tracking

​Install

​Set up

​Usage

​Verify

​What gets captured

​Limitations

​Run the example

Python

​Next steps

Python SDK Reference

Cost Tracking

Install

Set up

Usage

Verify

What gets captured

Limitations

Run the example

Next steps