AI APIs

Chat Completions API Cheat Sheet

Endpoints, parameters, streaming and error codes at a glance

The parameters that actually change behaviour, a working request in three languages, the error codes you will hit in production, and what to do about each one.

Intermediate 2 min read 12 Entries Version 1.0 Sabir Updated 7 4
Download PDF Export Markdown Export HTML

Core parameters

The ones that meaningfully change output. Everything else is situational.

Parameter What it does Sensible default
model Which model answers the request The newest one you can afford
messages The conversation so far, oldest first system + user
temperature Randomness. 0 = repeatable, 1 = creative 0 for extraction, 0.7 for writing
max_tokens Ceiling on the REPLY length only Set it — an unbounded reply is a runaway bill
stream Send tokens as they are produced true for anything user-facing
response_format Force valid JSON {"type":"json_object"} for pipelines
tools Functions the model may call Only what this request could need
seed Best-effort determinism Set when you need reproducibility

Token budgeting

The context window covers INPUT + OUTPUT together. A 128k window with a 120k prompt leaves you 8k of answer. Budget backwards from the reply length you need, and remember every prior turn you resend is billed again.

Code examples

Minimal request (Python)

The smallest thing that works, with streaming on.

Python chat.py Download 
from openai import OpenAI

client = OpenAI(api_key="YOUR_KEY")

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are concise."},
        {"role": "user", "content": "Explain vector embeddings in two sentences."},
    ],
    temperature=0.3,
    max_tokens=300,
    stream=True,
)

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

Minimal request (JavaScript)

JavaScript chat.mjs Download 
import OpenAI from 'openai';

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are concise.' },
    { role: 'user', content: 'Explain vector embeddings in two sentences.' },
  ],
  temperature: 0.3,
  max_tokens: 300,
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

Retry with backoff (Python)

Rate limits are normal, not exceptional. Handle them from day one.

Python retry.py Download 
import time, random

def with_backoff(fn, attempts=5):
    for i in range(attempts):
        try:
            return fn()
        except Exception as e:
            status = getattr(e, 'status_code', None)
            if status not in (429, 500, 502, 503, 529) or i == attempts - 1:
                raise
            # full jitter: avoids a thundering herd on recovery
            time.sleep(random.uniform(0, 2 ** i))

API reference

POST https://api.openai.com/v1/chat/completions

Sends a conversation and returns the next assistant message.

Authentication

Bearer token in the Authorization header

Parameters
NameType RequiredDescription
model string yes Model id, e.g. gpt-4o
messages array yes Ordered list of {role, content}
temperature number no 0–2. Lower is more deterministic
max_tokens integer no Ceiling on the reply
stream boolean no Server-sent events
Headers
HeaderValueNotes
Authorization Bearer $OPENAI_API_KEY Required
Content-Type application/json Required
Request 
curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
Response
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "model": "gpt-4o",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hello! How can I help?" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 8, "total_tokens": 17 }
}
Error codes
CodeMeaningWhat to do
401 Bad or missing API key Check the header name and that the key is not expired
400 Malformed request Usually a bad messages array or an unknown parameter
429 Rate or quota limit Exponential backoff with jitter; check your usage tier
500 / 503 Upstream failure Retry idempotently; do not retry non-idempotent side effects
context_length_exceeded Prompt + reply exceeds the window Trim history or summarise older turns
Rate limits: Per-model RPM and TPM, tier-dependent. Always read the x-ratelimit-* response headers rather than hard-coding a number.

Frequently asked questions

Why is my reply cut off mid-sentence?
You hit max_tokens. Check finish_reason — if it is "length", raise the ceiling or ask for a shorter answer.
Does temperature 0 guarantee identical output?
No. It makes sampling greedy but hardware and model updates still introduce variance. Use seed for best-effort reproducibility.

Resources

AI Models directory Compare context windows and pricing

Was this cheat sheet useful?

Comments

No comments yet — be the first.

Keep going

More cheat sheets

Browse all
Anthropic Messages API Cheat Sheet AI APIs · 2 min read · 18 Entries Streaming LLM Responses Cheat Sheet AI APIs · 1 min read · 14 Entries
Need a different cheat sheet? Tell us what you would like to see and we will build it — free.
Request a cheat sheet