Integrations
Groq
Trace Groq calls in Muster — either via the OpenAI-compatible endpoint or the Groq-native OpenInference instrumentation.
Groq hosts large language models on their LPU inference engine and exposes them via an OpenAI-compatible API. Muster has two ways to trace Groq calls.
Option 1: OpenAI SDK route
Use the Muster OpenAI wrapper pointed at Groq's base URL.
%pip install langfuse openai --upgradeimport os
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
os.environ["LANGFUSE_BASE_URL"] = "https://app.getmuster.io"
os.environ["GROQ_API_KEY"] = "gsk_..."from langfuse.openai import OpenAI
client = OpenAI(
base_url="https://api.groq.com/openai/v1",
api_key=os.environ["GROQ_API_KEY"],
)
completion = client.chat.completions.create(
model="llama3-8b-8192",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Write a poem about language models"},
],
)
print(completion.choices[0].message.content)Option 2: Native Groq SDK + OpenInference
%pip install groq langfuse openinference-instrumentation-groqfrom langfuse import get_client
from openinference.instrumentation.groq import GroqInstrumentor
langfuse = get_client()
assert langfuse.auth_check()
GroqInstrumentor().instrument()from groq import Groq
groq_client = Groq(api_key=os.environ["GROQ_API_KEY"])
chat_completion = groq_client.chat.completions.create(
messages=[{"role": "user", "content": "Explain the importance of fast language models"}],
model="llama-3.3-70b-versatile",
)
print(chat_completion.choices[0].message.content)Trace details
Muster displays request parameters, response content, token usage, and latency.
