How to beginner · 3 min read

How to classify text with Claude API

Q: How to classify text with Claude API

Use the anthropic Python SDK to classify text with Claude by sending a prompt that instructs the model to categorize the input. Create a client with your API key, call client.messages.create with model="claude-3-5-sonnet-20241022", and parse the response content for classification results.

Quick answer

Use the anthropic Python SDK to classify text with Claude by sending a prompt that instructs the model to categorize the input. Create a client with your API key, call client.messages.create with model="claude-3-5-sonnet-20241022", and parse the response content for classification results.

PREREQUISITES

Python 3.8+
Anthropic API key
pip install anthropic>=0.20

Setup

Install the anthropic SDK and set your API key as an environment variable.

Install the SDK: pip install anthropic
Set environment variable: export ANTHROPIC_API_KEY='your_api_key' (Linux/macOS) or set ANTHROPIC_API_KEY=your_api_key (Windows)

bash

pip install anthropic

output

Collecting anthropic
  Downloading anthropic-0.20.0-py3-none-any.whl (20 kB)
Installing collected packages: anthropic
Successfully installed anthropic-0.20.0

Step by step

This example shows how to classify text by prompting Claude to assign a category label. The prompt instructs Claude to respond with a single category based on the input text.

python

import os
import anthropic

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

text_to_classify = "I love sunny days and going to the beach."

prompt = f"Classify the following text into one of these categories: Weather, Sports, Food, Travel, or Other.\nText: {text_to_classify}\nCategory:" 

response = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=10,
    system="You are a helpful text classification assistant.",
    messages=[{"role": "user", "content": prompt}]
)

category = response.content[0].text.strip()
print(f"Text: {text_to_classify}")
print(f"Predicted category: {category}")

output

Text: I love sunny days and going to the beach.
Predicted category: Weather

Common variations

Use different Claude models like claude-sonnet-4-5 for potentially improved accuracy.
Adjust max_tokens to control response length.
Use async calls with asyncio and client.messages.acreate for concurrency.
Format prompt to request JSON output for structured classification.

python

import asyncio
import os
import anthropic

async def classify_text_async(text):
    client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])
    prompt = f"Classify the text into categories: Weather, Sports, Food, Travel, Other.\nText: {text}\nCategory:"
    response = await client.messages.acreate(
        model="claude-3-5-sonnet-20241022",
        max_tokens=10,
        system="You are a helpful text classification assistant.",
        messages=[{"role": "user", "content": prompt}]
    )
    return response.content[0].text.strip()

async def main():
    category = await classify_text_async("The pizza was delicious and cheesy.")
    print(f"Predicted category: {category}")

asyncio.run(main())

output

Predicted category: Food

Troubleshooting

If you get authentication errors, verify your ANTHROPIC_API_KEY environment variable is set correctly.
If the classification is off, refine your prompt to be more explicit or provide examples.
For rate limits, consider retrying with exponential backoff.
Ensure you use the system= parameter instead of a system role message.

✅

Key Takeaways

Use the anthropic SDK with client.messages.create to classify text via prompt engineering.
Set the system= parameter to guide Claude's behavior effectively.
Async calls enable concurrent classification for higher throughput.
Refine prompts and categories for better classification accuracy.
Always secure your API key via environment variables to avoid leaks.

Verified 2026-04 · claude-3-5-sonnet-20241022, claude-sonnet-4-5

Verify ↗