Skip to main content
The OpenInference Groq instrumentor traces calls made with the Groq Python SDK — model, token usage, and messages — as OTLP spans. Point the exporter at AgentMark and the traces arrive normalized.

​
Setup

1

Install the instrumentor and the OTLP exporter

pip install openinference-instrumentation-groq groq \
  opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
2

Point the exporter at AgentMark and instrument Groq

Use your AgentMark API key and app id from project settings.
from openinference.instrumentation.groq import GroqInstrumentor
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

provider = TracerProvider()
provider.add_span_processor(
    BatchSpanProcessor(
        OTLPSpanExporter(
            endpoint="https://api.agentmark.co/v1/traces",
            headers={
                "Authorization": "<YOUR_API_KEY>",  # raw key, no "Bearer" prefix
                "X-Agentmark-App-Id": "<YOUR_APP_ID>",
            },
        )
    )
)

GroqInstrumentor().instrument(tracer_provider=provider)
3

Run your calls

Use the Groq client as usual — client.chat.completions.create(...). Each call arrives in AgentMark as a span, grouped into a trace. See Traces and logs.
from groq import Groq

client = Groq(api_key="<GROQ_API_KEY>")
client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

​
What AgentMark captures

Groq spans use the OpenInference attribute conventions — model, token usage, input and output messages, tool calls, settings, and span kind are all mapped onto AgentMark’s normalized trace fields, and token counts feed cost tracking. See OpenInference for the full attribute mapping.

​
Next steps

OpenInference

How AgentMark reads OpenInference attributes

Traces and logs

Explore traces once they arrive

​
Have questions?

Reach out any time: