OpenAI

SideSeat automatically extracts model information, token usage, and costs from OpenAI API calls.

Prerequisites

• SideSeat running locally (sideseat)
• SDK installed (pip install sideseat / uv add sideseat or npm install @sideseat/sdk)
• OpenAI API credentials configured

Usage with OpenAI SDK

Python

from sideseat import SideSeat
SideSeat()

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

JavaScript

import { init } from '@sideseat/sdk';
init();

import OpenAI from 'openai';

const client = new OpenAI();
const response = await client.chat.completions.create({
  model: 'gpt-5-mini',
  messages: [{ role: 'user', content: 'Hello!' }]
});
console.log(response.choices[0].message.content);

Extracted Attributes

SideSeat extracts these attributes from OpenAI traces:

Attribute	Source
gen_ai.system	openai
gen_ai.request.model	Request model parameter
gen_ai.response.model	Response model field
gen_ai.usage.input_tokens	usage.prompt_tokens
gen_ai.usage.output_tokens	usage.completion_tokens
gen_ai.request.temperature	Temperature parameter
gen_ai.request.max_tokens	Max tokens parameter

Streaming

Streaming responses are fully captured:

stream = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Token counts are aggregated from stream chunks.

Function Calling

Tool calls are traced with full details:

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            }
        }
    }
}]

response = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[{"role": "user", "content": "What's the weather in Paris?"}],
    tools=tools
)

Vision

Image inputs are captured (image data base64-encoded):

response = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}}
        ]
    }]
)

Cost Calculation

SideSeat automatically calculates costs based on:

• Model pricing (updated regularly)
• Input token count
• Output token count

Costs appear in the trace detail view.

Next Steps

• First Run — get started with SideSeat
• Python SDK — SDK reference