Your First Claude API Call in TypeScript and Python

Large language model APIs all follow the same basic shape: you send a list of messages and get a message back. This guide uses the official Anthropic SDK to call Claude, but the ideas carry over to any provider.

1. Install the SDK and set your key

# TypeScript / Node.js
npm install @anthropic-ai/sdk

# Python
pip install anthropic

# Both SDKs read the key from the environment
export ANTHROPIC_API_KEY="sk-ant-..."

Never hard-code the key in source files. Keep it in an environment variable or your platform's secret manager.

2. Send a message (TypeScript)

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic(); // reads ANTHROPIC_API_KEY

const response = await client.messages.create({
  model: 'claude-opus-5-5',
  max_tokens: 16000,
  messages: [{ role: 'user', content: 'Explain a REST API in two sentences.' }],
});

// content is an array of blocks; narrow to text blocks before reading .text
for (const block of response.content) {
  if (block.type === 'text') console.log(block.text);
}

3. The same call in Python

import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=16000,
    messages=[{"role": "user", "content": "Explain a REST API in two sentences."}],
)

for block in response.content:
    if block.type == "text":
        print(block.text)

4. Add a system prompt

The system parameter sets the role, tone and rules for the whole conversation. It sits outside the messages array.

const response = await client.messages.create({
  model: 'claude-opus-5-5',
  max_tokens: 16000,
  system: 'You are a senior backend engineer. Answer with short, practical examples.',
  messages: [{ role: 'user', content: 'How do I paginate a SQL query?' }],
});

5. Multi-turn conversations

The API is stateless. To continue a chat, send the whole history every time, alternating user and assistant roles.

const messages: Anthropic.MessageParam[] = [
  { role: 'user', content: 'My name is Asha.' },
  { role: 'assistant', content: 'Nice to meet you, Asha!' },
  { role: 'user', content: 'What is my name?' },
];

const reply = await client.messages.create({ model: 'claude-opus-5-5', max_tokens: 16000, messages });

What comes back

• content - an array of blocks (text, tool_use, thinking...).
• stop_reason - why generation stopped: end_turn, max_tokens, tool_use or refusal.
• usage - input and output token counts, which is what you are billed for.

Always check stop_reason before trusting the output. A max_tokens stop means the answer was cut off.