Skip to main content
LiteLLM routes calls to 100+ model providers behind one OpenAI-style interface. The OpenInference LiteLLM instrumentor captures each litellm.completion call as an OTLP span — model, token usage, and messages. Point the exporter at AgentMark and the traces arrive normalized. The example below is Python.

​
Setup

1

Install the instrumentor and the OTLP exporter

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

Point the exporter at AgentMark and instrument LiteLLM

Use your AgentMark API key and app id from project settings.
from openinference.instrumentation.litellm import LiteLLMInstrumentor
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>",
            },
        )
    )
)

LiteLLMInstrumentor().instrument(tracer_provider=provider)
3

Run your calls

Call litellm.completion (or acompletion) as usual. Each call arrives in AgentMark as a span, grouped into a trace. See Traces and logs.

​
What AgentMark captures

LiteLLM 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: