sentrinode-llm

Drop-in observability for your LLM calls. Two lines, and every Anthropic / OpenAI request is traced with model, token usage, latency, finish reason, and computed USD cost — using the OpenTelemetry GenAI semantic conventions.

Install

pip install sentrinode-llm        # add [anthropic] and/or [openai] as needed

Use

import sentrinode_llm
sentrinode_llm.instrument()   # reads SENTRINODE_API_KEY + SENTRINODE_TENANT

import anthropic
client = anthropic.Anthropic()
client.messages.create(            # ← automatically traced
    model="claude-haiku-4-5-20251001",
    max_tokens=256,
    messages=[{"role": "user", "content": "hello"}],
)

That's it — no wrapping your calls, no decorators. The same works for OpenAI:

from openai import OpenAI
OpenAI().chat.completions.create(model="gpt-4o-mini", messages=[...])  # traced

Configure

Or pass them directly: sentrinode_llm.instrument(api_key=..., tenant=...).

What gets recorded

Each call becomes one OpenTelemetry span:

Cost is computed from pricing.py. Override any model:

sentrinode_llm.set_price("my-model", input_per_1m=2.0, output_per_1m=8.0)

Not yet

• Streaming responses pass through untraced (usage isn't known until the stream ends — coming next).
• Async clients and embeddings — next iteration.