Code beginner · 3 min read

How to use Claude 3.5 Sonnet in python

Q: How to use Claude 3.5 Sonnet in python

Use the anthropic Python SDK to create a client with your API key, then call client.messages.create with model="claude-3-5-sonnet-20241022" and your messages to get completions.

Direct answer

Use the anthropic Python SDK to create a client with your API key, then call client.messages.create with model="claude-3-5-sonnet-20241022" and your messages to get completions.

Setup

Install

bash

pip install anthropic

Env vars

ANTHROPIC_API_KEY

Imports

python

import os
import anthropic

Examples

inWhat is the capital of France?

outThe capital of France is Paris.

inWrite a Python function to reverse a string.

outHere's a Python function to reverse a string: ```python def reverse_string(s): return s[::-1] ```

inExplain quantum computing in simple terms.

outQuantum computing uses quantum bits that can be both 0 and 1 at the same time, allowing it to solve certain problems much faster than classical computers.

Integration steps

Install the Anthropic Python SDK and set your API key in the environment variable ANTHROPIC_API_KEY.
Import the anthropic library and initialize the client with your API key from os.environ.
Prepare your conversation messages as a list of dictionaries with roles and content.
Call client.messages.create with model="claude-3-5-sonnet-20241022", system prompt, max_tokens, and messages.
Extract the generated text from the response's content field.
Use or display the returned text as needed in your application.

Full code

python

import os
import anthropic

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

system_prompt = "You are a helpful assistant."
user_message = "Explain the benefits of using Claude 3.5 Sonnet in Python."

response = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=300,
    system=system_prompt,
    messages=[{"role": "user", "content": user_message}]
)

print("Response from Claude 3.5 Sonnet:")
print(response.content[0].text)

output

Response from Claude 3.5 Sonnet:
Claude 3.5 Sonnet offers advanced natural language understanding and generation capabilities, making it ideal for Python developers to build conversational AI, automate tasks, and generate code efficiently.

API trace

Request

json

{"model": "claude-3-5-sonnet-20241022", "max_tokens": 300, "system": "You are a helpful assistant.", "messages": [{"role": "user", "content": "Explain the benefits of using Claude 3.5 Sonnet in Python."}]}

Response

json

{"id": "chatcmpl-xxx", "object": "chat.completion", "model": "claude-3-5-sonnet-20241022", "created": 1680000000, "choices": [{"index": 0, "message": {"role": "assistant", "content": ["Claude 3.5 Sonnet offers advanced natural language understanding and generation capabilities..."]}, "finish_reason": "stop"}], "usage": {"prompt_tokens": 50, "completion_tokens": 100, "total_tokens": 150}}

Extractresponse.content[0].text

Variants

Streaming response with Claude 3.5 Sonnet ›

Use streaming to display partial results immediately for better user experience with long responses.

python

import os
import anthropic

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

system_prompt = "You are a helpful assistant."
user_message = "Tell me a story about a robot learning to code."

stream = client.messages.stream(
    model="claude-3-5-sonnet-20241022",
    max_tokens=500,
    system=system_prompt,
    messages=[{"role": "user", "content": user_message}]
)

print("Streaming response:")
for chunk in stream:
    print(chunk.content[0].text, end='', flush=True)

Async usage of Claude 3.5 Sonnet ›

Use async calls when integrating into asynchronous Python applications to improve concurrency.

python

import os
import asyncio
import anthropic

async def main():
    client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])
    response = await client.messages.acreate(
        model="claude-3-5-sonnet-20241022",
        max_tokens=200,
        system="You are a helpful assistant.",
        messages=[{"role": "user", "content": "What is AI?"}]
    )
    print(response.content[0].text)

asyncio.run(main())

Using Claude 3.5 Haiku model for creative tasks ›

Use the haiku variant for poetry or creative writing tasks where style matters.

python

import os
import anthropic

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

response = client.messages.create(
    model="claude-3-5-haiku-20241022",
    max_tokens=100,
    system="You are a creative poetry assistant.",
    messages=[{"role": "user", "content": "Write a haiku about spring."}]
)

print(response.content[0].text)

Performance

Latency~1.2 seconds for typical 200-token completions

Cost~$0.003 per 1000 tokens

Rate limitsTier 1: 300 requests per minute, 60,000 tokens per minute

Use concise prompts to reduce token usage.
Limit <code>max_tokens</code> to only what you need.
Reuse context efficiently by summarizing prior conversation.

Approach	Latency	Cost/call	Best for
Standard call	~1.2s	~$0.003/1k tokens	General purpose completions
Streaming	Starts immediately, total ~1.2s	~$0.003/1k tokens	Long responses with better UX
Async call	~1.2s (concurrent)	~$0.003/1k tokens	Concurrent or async apps

✓

Quick tip

Always set a clear system prompt with <code>system=</code> to guide Claude 3.5 Sonnet's behavior effectively.

⚠

Common mistake

Beginners often forget to use the <code>system=</code> parameter and instead try to pass system instructions as a message, which Claude's SDK does not support.

Verified 2026-04 · claude-3-5-sonnet-20241022

Verify ↗