Musterby Elitery
Integrations

TrueFoundry

Trace LLM calls routed through TrueFoundry's enterprise AI gateway in Muster.

TrueFoundry's AI Gateway routes LLM requests through a unified OpenAI-compatible endpoint with enterprise-grade rate limits, budgets, and analytics. Trace its calls in Muster via the OpenAI wrapper.

Setup

%pip install openai langfuse
import 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["TRUEFOUNDRY_API_KEY"] = "your-token"
os.environ["TRUEFOUNDRY_BASE_URL"] = "https://your-control-plane.truefoundry.cloud/api/llm"
from langfuse.openai import OpenAI

client = OpenAI(
    api_key=os.environ["TRUEFOUNDRY_API_KEY"],
    base_url=os.environ["TRUEFOUNDRY_BASE_URL"],
)

Example

response = client.chat.completions.create(
    model="openai-main/gpt-4o",
    messages=[{"role": "user", "content": "Your query"}],
    max_tokens=500,
)
print(response.choices[0].message.content)

The integration captures token usage, latency, cost analytics, and the gateway's rate-limit and budget metadata.

See also