OpenAI

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

Setup

pip install "glassflow-rius[openai]" openai

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

npm install @arizeai/openinference-instrumentation-openai

import { init } from '@glassflow-ai/rius'
import OpenAI from 'openai'
 
const rius = init({ apiKey: 'gf_...', serviceName: 'my-agent' })
const client = new OpenAI()  // use the client exactly as before

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 Python 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},
)

const stream = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  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.