OpenAI API

Build AI applications using OpenAI's APIs with Python or TypeScript SDKs.

Quick Start

Installation

# Python
pip install openai

# TypeScript/Node.js
npm install openai

Client Setup

Python:

from openai import OpenAI

client = OpenAI()  # Uses OPENAI_API_KEY env var
# Or: client = OpenAI(api_key="sk-...")

TypeScript:

import OpenAI from 'openai';

const client = new OpenAI();  // Uses OPENAI_API_KEY env var
// Or: new OpenAI({ apiKey: 'sk-...' })

Chat Completions

Basic chat completion:

Python:

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

TypeScript:

const response = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [
        { role: 'system', content: 'You are a helpful assistant.' },
        { role: 'user', content: 'Hello!' }
    ]
});
console.log(response.choices[0].message.content);

Streaming

Python:

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

TypeScript:

const stream = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Tell me a story' }],
    stream: true
});
for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Tool Use / Function Calling

Python:

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

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What's the weather in Paris?"}],
    tools=tools
)

# Check if tool call requested
if response.choices[0].message.tool_calls:
    tool_call = response.choices[0].message.tool_calls[0]
    # Execute function, then send result back
    messages.append(response.choices[0].message)
    messages.append({
        "role": "tool",
        "tool_call_id": tool_call.id,
        "content": '{"temp": 22, "condition": "sunny"}'
    })

TypeScript:

const tools: OpenAI.ChatCompletionTool[] = [{
    type: 'function',
    function: {
        name: 'get_weather',
        description: 'Get current weather for a location',
        parameters: {
            type: 'object',
            properties: {
                location: { type: 'string', description: 'City name' }
            },
            required: ['location']
        }
    }
}];

const response = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: "What's the weather in Paris?" }],
    tools
});

if (response.choices[0].message.tool_calls) {
    const toolCall = response.choices[0].message.tool_calls[0];
    // Execute function, then continue conversation
}

Vision (Image Input)

Python:

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
        ]
    }]
)

For base64 images: "url": "data:image/jpeg;base64,{base64_string}"

Structured Outputs (JSON Mode)

Python:

from pydantic import BaseModel

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

response = client.beta.chat.completions.parse(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Create a meeting for tomorrow"}],
    response_format=CalendarEvent
)
event = response.choices[0].message.parsed

TypeScript (with Zod):

import { zodResponseFormat } from 'openai/helpers/zod';
import { z } from 'zod';

const CalendarEvent = z.object({
    name: z.string(),
    date: z.string(),
    participants: z.array(z.string())
});

const response = await client.beta.chat.completions.parse({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Create a meeting for tomorrow' }],
    response_format: zodResponseFormat(CalendarEvent, 'event')
});
const event = response.choices[0].message.parsed;

Models

Chat/Completion Models

Reasoning Models

Specialized Models

Feature References

• Advanced chat patterns: See references/chat-completions.md
• Image generation (DALL-E): See references/images.md
• Audio (Whisper/TTS): See references/audio.md
• Embeddings: See references/embeddings.md
• Assistants API: See references/assistants.md
• Fine-tuning: See references/fine-tuning.md

Error Handling

Python:

from openai import APIError, RateLimitError, APIConnectionError

try:
    response = client.chat.completions.create(...)
except RateLimitError:
    # Implement backoff/retry
    pass
except APIConnectionError:
    # Network issue
    pass
except APIError as e:
    print(f"API error: {e.status_code} - {e.message}")

TypeScript:

import OpenAI from 'openai';

try {
    const response = await client.chat.completions.create({...});
} catch (error) {
    if (error instanceof OpenAI.RateLimitError) {
        // Implement backoff/retry
    } else if (error instanceof OpenAI.APIConnectionError) {
        // Network issue
    } else if (error instanceof OpenAI.APIError) {
        console.error(`API error: ${error.status} - ${error.message}`);
    }
}

Common Parameters