Google Gen AI | Respan Docs

The official Google Gen AI SDK is the client for Google’s Gemini models, supporting text, multimodal, tool use, and structured outputs. Respan gives you full observability over every Gemini call, streamed response, and tool invocation — and gateway routing through the Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai opentelemetry-instrumentation-google-generativeai google-genai

Set environment variables

$ export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

GOOGLE_API_KEY is used for Gemini requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 import os
2 from google import genai
3 from respan import Respan
4 from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAiInstrumentor
5 
6 respan = Respan(instrumentations=[GoogleGenerativeAiInstrumentor()])
7 
8 client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
9 
10 response = client.models.generate_content(
11     model="gemini-2.5-flash",
12     contents="Say hello in three languages.",
13 )
14 print(response.text)
15 respan.flush()

View your trace

Open the Traces page to see your auto-instrumented Gemini spans with prompts, tokens, and tool calls.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `GoogleGenerativeAiInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAiInstrumentor
3 
4 respan = Respan(
5     instrumentations=[GoogleGenerativeAiInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "gemini-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from google import genai
2 from respan import Respan, propagate_attributes
3 from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAiInstrumentor
4 
5 respan = Respan(instrumentations=[GoogleGenerativeAiInstrumentor()])
6 client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
7 
8 def handle_request(user_id: str, question: str):
9     with propagate_attributes(
10         customer_identifier=user_id,
11         thread_identifier="conv_abc_123",
12         metadata={"plan": "pro"},
13     ):
14         response = client.models.generate_content(
15             model="gemini-2.5-flash",
16             contents=question,
17         )
18         print(response.text)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.