Claude API cheatsheet

Claude API: Streaming

4 common Claude API tasks.

Stream text (Python)

Print text as it is generated. Use streaming for long outputs and high max_tokens, which avoids request timeouts.

with client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=64000,
    messages=[{"role": "user", "content": "Write a story"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

Stream and get the full message

Stream for the timeout benefits, then read the complete message at the end.

with client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=64000,
    messages=[{"role": "user", "content": "Write a long report"}],
) as stream:
    message = stream.get_final_message()
print(message.usage.output_tokens)

Stream asynchronously

Use the async client with async with and async for.

async_client = anthropic.AsyncAnthropic()

async with async_client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=64000,
    messages=[{"role": "user", "content": "Write a story"}],
) as stream:
    async for text in stream.text_stream:
        print(text, end="", flush=True)

Stream in TypeScript

Subscribe to text events, then await the final message.

const stream = client.messages.stream({
  model: "claude-opus-5-5",
  max_tokens: 64000,
  messages: [{ role: "user", content: "Write a story" }],
});

stream.on("text", (text) => process.stdout.write(text));
const message = await stream.finalMessage();