OpenAI

Trace every OpenAI client call with Rius without touching your call sites.

Setup

pip install "glassflow-ai[openai]"

import glassflow
from openai import OpenAI
 
glassflow.init(api_key="glassflow_...", service_name="my-agent")
client = OpenAI()  # use the client exactly as before

init() detects the installed extra and instruments the client library process-wide; every call from anywhere in your process is traced.

What gets captured

Each chat completion becomes an LLM-kind span carrying the model, token usage, and input/output messages; cost is computed server-side from the model and tokens. On streamed calls the instrumentor also records a first-token event, so time to first token works without any manual code.

Streaming and token usage

Streamed responses do not include usage by default; ask OpenAI to send it with the final chunk:

stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    stream=True,
    stream_options={"include_usage": True},
)

Without it, streamed spans have no token counts, and no tokens means no cost.

Verify

Run one call, then open the trace in the console: the span shows the resolved model (e.g. gpt-4o-mini-2024-07-18), input/output token counts, and a cost. Wrap the call in @observe to see it nested inside your agent’s run instead of as a standalone trace.