OpenAI SDK: How the OpenAI API works

Under every chatbot, agent and “AI feature” is the same exchange: your code sends an HTTP request containing a model name and some input, and gets back output plus a count of tokens used. That is all the model does. It has no memory between calls, it cannot run your code, and it charges per token. Understanding this exchange precisely makes every later topic (tools, memory, streaming, cost) obvious.

1. One request, end to end

2. See the actual request and response

Every runnable example in this guide uses fake_openai.py (part 02), which runs the real openai SDK against a local fake server. Nothing leaves your machine, no key is needed, and you can inspect the exact JSON the SDK sends.

what goes over the wire

import json
from fake_openai import fake_client          # real code: from openai import OpenAI; client = OpenAI()

client = fake_client(script=["Delivered on 12 Oct; refund of INR 1,500 approved."])
response = client.responses.create(
    model="gpt-5.6-luna",
    instructions="Answer in one sentence.",
    input="What happened with order 1042?",
)

sent = client.fake.requests[0]
print("POST", sent["path"])
print(json.dumps(sent["body"], indent=2))
print("---")
print(type(response).__name__, response.id)
print("output items:", [item.type for item in response.output])
print("output_text: ", response.output_text)
print("usage:       ", response.usage.input_tokens, "in /", response.usage.output_tokens, "out")

Output

POST /v1/responses
{
  "input": "What happened with order 1042?",
  "instructions": "Answer in one sentence.",
  "model": "gpt-5.6-luna"
}
---
Response resp_2
output items: ['message']
output_text:  Delivered on 12 Oct; refund of INR 1,500 approved.
usage:        13 in / 12 out

output_text is a convenience property that joins the text of all message items. output is the real structure: a list of items such as messages, function calls, reasoning and web search results. Later parts use those other item types.

3. Tokens: the unit of everything

4. The model is stateless

two separate calls know nothing about each other

from fake_openai import fake_client

client = fake_client(script=["Nice to meet you, Asha!", "I don't know your name; you haven't told me."])
first = client.responses.create(model="gpt-5.6-luna", input="Hi, my name is Asha.")
second = client.responses.create(model="gpt-5.6-luna", input="What is my name?")
print(first.output_text)
print(second.output_text)
print("second request contained:", client.fake.requests[1]["body"]["input"])

Output

Nice to meet you, Asha!
I don't know your name; you haven't told me.
second request contained: What is my name?

The second request contained only the second question, so a real model could not know the name either. “Chat memory” is always your code (or OpenAI’s stored conversation state) resending earlier turns. Part 15 covers both approaches and what each costs.

5. The constraints you design around

Recap