OpenAI API Cheat Sheet: GPT-4o, Tools & Assistants

Quick reference tables

Models

Chat Completions — key parameters

Roles in messages

Assistants API — key concepts

Embeddings

Image generation (DALL-E 3)

Detailed sections

Basic chat completion (Node.js)

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "system", content: "You are a helpful coding assistant." },
    { role: "user", content: "Explain the difference between == and === in JavaScript." },
  ],
  max_completion_tokens: 512,
});

console.log(response.choices[0].message.content);

Streaming

const stream = await client.chat.completions.create({
  model: "gpt-4o",
  stream: true,
  messages: [{ role: "user", content: "Write a haiku about databases." }],
});

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

Structured output (JSON schema)

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "user", content: "Extract: John Doe, john@example.com, Senior Engineer" },
  ],
  response_format: {
    type: "json_schema",
    json_schema: {
      name: "contact",
      schema: {
        type: "object",
        properties: {
          name: { type: "string" },
          email: { type: "string" },
          title: { type: "string" },
        },
        required: ["name", "email", "title"],
        additionalProperties: false,
      },
      strict: true,
    },
  },
});

const contact = JSON.parse(response.choices[0].message.content);

Function calling / tool use

const tools = [
  {
    type: "function",
    function: {
      name: "search_database",
      description: "Search the product database",
      parameters: {
        type: "object",
        properties: {
          query: { type: "string" },
          limit: { type: "integer", default: 10 },
        },
        required: ["query"],
      },
    },
  },
];

const response = await client.chat.completions.create({
  model: "gpt-4o",
  tools,
  tool_choice: "auto",
  messages: [{ role: "user", content: "Find products under $50" }],
});

const toolCall = response.choices[0].message.tool_calls?.[0];
if (toolCall) {
  const args = JSON.parse(toolCall.function.arguments);
  // call your actual function: searchDatabase(args.query, args.limit)
}

Embeddings — semantic search

// Create embeddings
const embedding = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: "How do I reset my password?",
});

const vector = embedding.data[0].embedding; // float array

// Compare two texts (cosine similarity)
function cosineSimilarity(a, b) {
  const dot = a.reduce((sum, val, i) => sum + val * b[i], 0);
  const magA = Math.sqrt(a.reduce((sum, val) => sum + val * val, 0));
  const magB = Math.sqrt(b.reduce((sum, val) => sum + val * val, 0));
  return dot / (magA * magB);
}

Assistants API — simple agent

// 1. Create an Assistant (do this once)
const assistant = await client.beta.assistants.create({
  name: "Code Reviewer",
  instructions: "Review code for bugs, style issues, and security vulnerabilities.",
  model: "gpt-4o",
  tools: [{ type: "code_interpreter" }],
});

// 2. Create a Thread per user session
const thread = await client.beta.threads.create();

// 3. Add user message
await client.beta.threads.messages.create(thread.id, {
  role: "user",
  content: "Review this function: function add(a,b){return a+b}",
});

// 4. Run the Assistant
const run = await client.beta.threads.runs.createAndPoll(thread.id, {
  assistant_id: assistant.id,
});

// 5. Get the response
if (run.status === "completed") {
  const messages = await client.beta.threads.messages.list(thread.id);
  console.log(messages.data[0].content[0].text.value);
}

Image generation

const image = await client.images.generate({
  model: "dall-e-3",
  prompt: "A futuristic server room with glowing blue circuits",
  size: "1792x1024",
  quality: "hd",
  style: "vivid",
  n: 1,
});

console.log(image.data[0].url);

Audio transcription (Whisper)

import fs from "fs";

const transcription = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: fs.createReadStream("recording.mp3"),
  language: "en", // optional
  response_format: "text",
});

console.log(transcription);

Text-to-speech

import fs from "fs";

const audio = await client.audio.speech.create({
  model: "tts-1",
  voice: "nova", // alloy, echo, fable, onyx, nova, shimmer
  input: "Hello, this is a test of the text to speech API.",
  speed: 1.0, // 0.25–4.0
});

const buffer = Buffer.from(await audio.arrayBuffer());
fs.writeFileSync("output.mp3", buffer);

Environment setup

# Install SDK
npm install openai

# Set API key
export OPENAI_API_KEY=sk-...

# Python SDK
pip install openai

python3 -c "
import openai
client = openai.OpenAI()
r = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role':'user','content':'Hello'}]
)
print(r.choices[0].message.content)
"

System_Continuity

Next_Recommended_Node

Gemini API Cheat Sheet: 2.5 Pro, Vision & Grounding

Complete Google Gemini reference — Gemini 2.5 Pro and Flash models, generateContent, streaming, vision, JSON output, function calling, Search grounding, and Gemini CLI.

Vishnu Damwala

5m read

Cheatsheet 5m

Claude API Cheat Sheet: SDK, CLI, MCP & Prompting

Log_Access

Cheatsheet 5m

curl Cheat Sheet: API Testing, Auth & File Upload

Log_Access

Browse the full manifest