G
Integration
Google Gemini
Automatic tracing for Google Gemini API calls including Gemini 1.5 Pro, Flash, and multimodal capabilities.
Prerequisites
- Google AI API key
- Lanternfish SDK installed
1
Install the SDK
bash
pip install "lanternfish[gemini]"2
Initialize with auto-instrument
python
import os
import lanternfish
from google import genai
# Simply call instrument() and Gemini is auto-traced!
lanternfish.instrument(
api_key=os.environ["LANTERNFISH_API_KEY"],
endpoint=os.environ["LANTERNFISH_ENDPOINT"],
)
client = genai.Client()3
Use as normal — tracing is automatic
python
# Google Gemini calls are automatically traced
response = client.models.generate_content(
model="gemini-2.5-flash",
contents="Explain quantum computing in simple terms"
)
# Captures: model metadata, prompt/response tokens, latency
print(response.text)What Lanternfish captures
- Complete trace timeline
- Token usage and cost
- Latency metrics
- Tool and function calls
- Error tracking
- Model information