Frameworks & Platforms
OpenLLMetry
Trace TokenLab OpenAI-compatible requests with OpenLLMetry
Overview
Configure the OpenAI SDK with TokenLab /v1, then use OpenLLMetry to record those SDK calls.
Installation
pip install opentelemetry-instrumentation-openai opentelemetry-sdk openaiEnvironment
export TOKENLAB_API_KEY="sk-your-tokenlab-key"Example
This standalone example writes spans to your terminal. If your application already has an OpenTelemetry tracer provider, reuse that provider and its exporter.
import os
from openai import OpenAI
from opentelemetry import trace
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor
tracer_provider = TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))
trace.set_tracer_provider(tracer_provider)
OpenAIInstrumentor().instrument()
client = OpenAI(
api_key=os.environ["TOKENLAB_API_KEY"],
base_url="https://api.tokenlab.sh/v1",
)
client.chat.completions.create(
model="claude-sonnet-5",
messages=[{"role": "user", "content": "Trace this request"}],
)Endpoint Notes
Use this path for OpenAI SDK-compatible TokenLab calls. For TokenLab native endpoints, instrument the HTTP or SDK client that actually sends those requests.