Frameworks & Platforms
Langfuse
Trace TokenLab OpenAI-compatible requests with Langfuse
Overview
Langfuse can trace OpenAI SDK calls after the SDK Base URL is changed to TokenLab /v1.
Installation
pip install langfuse openaiEnvironment
export LANGFUSE_SECRET_KEY="sk-lf-..."
export LANGFUSE_PUBLIC_KEY="pk-lf-..."
export LANGFUSE_BASE_URL="https://cloud.langfuse.com"
export TOKENLAB_API_KEY="sk-your-tokenlab-key"Example
import os
from langfuse import get_client, observe
from langfuse.openai import OpenAI
client = OpenAI(
api_key=os.environ["TOKENLAB_API_KEY"],
base_url="https://api.tokenlab.sh/v1",
)
@observe()
def story():
return client.chat.completions.create(
model="claude-sonnet-5",
messages=[{"role": "user", "content": "Write a short haiku."}],
).choices[0].message.content
print(story())
get_client().flush()Endpoint Notes
This page covers Langfuse tracing for the OpenAI SDK path. If your application uses TokenLab native Responses, Anthropic Messages, or Gemini endpoints, make sure your instrumentation captures that client call path.