claude-api/python/claude-api/README.md

Claude API — Python

Installation

pip install anthropic

Client Initialization

import anthropic

# Default (uses ANTHROPIC_API_KEY env var)
client = anthropic.Anthropic()

# Explicit API key
client = anthropic.Anthropic(api_key="your-api-key")

# Async client
async_client = anthropic.AsyncAnthropic()

---

Basic Message Request

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "What is the capital of France?"}
    ]
)
print(response.content[0].text)

---

System Prompts

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    system="You are a helpful coding assistant. Always provide examples in Python.",
    messages=[{"role": "user", "content": "How do I read a JSON file?"}]
)

---

Vision (Images)

Base64

import base64

with open("image.png", "rb") as f:
    image_data = base64.standard_b64encode(f.read()).decode("utf-8")

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "image",
                "source": {
                    "type": "base64",
                    "media_type": "image/png",
                    "data": image_data
                }
            },
            {"type": "text", "text": "What's in this image?"}
        ]
    }]
)

URL

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "image",
                "source": {
                    "type": "url",
                    "url": "https://example.com/image.png"
                }
            },
            {"type": "text", "text": "Describe this image"}
        ]
    }]
)

---

Prompt Caching

Cache large context to reduce costs (up to 90% savings).

Automatic Caching (Recommended)

Use top-level cache_control to automatically cache the last cacheable block in the request — no need to annotate individual content blocks:

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    cache_control={"type": "ephemeral"},  # auto-caches the last cacheable block
    system="You are an expert on this large document...",
    messages=[{"role": "user", "content": "Summarize the key points"}]
)

Manual Cache Control

For fine-grained control, add cache_control to specific content blocks:

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    system=[{
        "type": "text",
        "text": "You are an expert on this large document...",
        "cache_control": {"type": "ephemeral"}  # default TTL is 5 minutes
    }],
    messages=[{"role": "user", "content": "Summarize the key points"}]
)

# With explicit TTL (time-to-live)
response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    system=[{
        "type": "text",
        "text": "You are an expert on this large document...",
        "cache_control": {"type": "ephemeral", "ttl": "1h"}  # 1 hour TTL
    }],
    messages=[{"role": "user", "content": "Summarize the key points"}]
)

---

Extended Thinking

Opus 4.6 and Sonnet 4.6: Use adaptive thinking. budget_tokens is deprecated on both Opus 4.6 and Sonnet 4.6. Older models: Use thinking: {type: "enabled", budget_tokens: N} (must be < max_tokens, min 1024).

# Opus 4.6: adaptive thinking (recommended)
response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=16000,
    thinking={"type": "adaptive"},
    output_config={"effort": "high"},  # low | medium | high | max
    messages=[{"role": "user", "content": "Solve this step by step..."}]
)

# Access thinking and response
for block in response.content:
    if block.type == "thinking":
        print(f"Thinking: {block.thinking}")
    elif block.type == "text":
        print(f"Response: {block.text}")

---

Error Handling

import anthropic

try:
    response = client.messages.create(...)
except anthropic.BadRequestError as e:
    print(f"Bad request: {e.message}")
except anthropic.AuthenticationError:
    print("Invalid API key")
except anthropic.PermissionDeniedError:
    print("API key lacks required permissions")
except anthropic.NotFoundError:
    print("Invalid model or endpoint")
except anthropic.RateLimitError as e:
    retry_after = int(e.response.headers.get("retry-after", "60"))
    print(f"Rate limited. Retry after {retry_after}s.")
except anthropic.APIStatusError as e:
    if e.status_code >= 500:
        print(f"Server error ({e.status_code}). Retry later.")
    else:
        print(f"API error: {e.message}")
except anthropic.APIConnectionError:
    print("Network error. Check internet connection.")

---

Multi-Turn Conversations

The API is stateless — send the full conversation history each time.

class ConversationManager:
    """Manage multi-turn conversations with the Claude API."""

    def __init__(self, client: anthropic.Anthropic, model: str, system: str = None):
        self.client = client
        self.model = model
        self.system = system
        self.messages = []

    def send(self, user_message: str, **kwargs) -> str:
        """Send a message and get a response."""
        self.messages.append({"role": "user", "content": user_message})

        response = self.client.messages.create(
            model=self.model,
            max_tokens=kwargs.get("max_tokens", 1024),
            system=self.system,
            messages=self.messages,
            **kwargs
        )

        assistant_message = response.content[0].text
        self.messages.append({"role": "assistant", "content": assistant_message})

        return assistant_message

# Usage
conversation = ConversationManager(
    client=anthropic.Anthropic(),
    model="claude-opus-4-6",
    system="You are a helpful assistant."
)

response1 = conversation.send("My name is Alice.")
response2 = conversation.send("What's my name?")  # Claude remembers "Alice"

Rules:

• Messages must alternate between user and assistant
• First message must be user

---

Compaction (long conversations)

Beta, Opus 4.6 only. When conversations approach the 200K context window, compaction automatically summarizes earlier context server-side. The API returns a compaction block; you must pass it back on subsequent requests — append response.content, not just the text.

import anthropic

client = anthropic.Anthropic()
messages = []

def chat(user_message: str) -> str:
    messages.append({"role": "user", "content": user_message})

    response = client.beta.messages.create(
        betas=["compact-2026-01-12"],
        model="claude-opus-4-6",
        max_tokens=4096,
        messages=messages,
        context_management={
            "edits": [{"type": "compact_20260112"}]
        }
    )

    # Append full content — compaction blocks must be preserved
    messages.append({"role": "assistant", "content": response.content})

    return next(block.text for block in response.content if block.type == "text")

# Compaction triggers automatically when context grows large
print(chat("Help me build a Python web scraper"))
print(chat("Add support for JavaScript-rendered pages"))
print(chat("Now add rate limiting and error handling"))

---

Stop Reasons

The stop_reason field in the response indicates why the model stopped generating:

Value	Meaning
end_turn	Claude finished its response naturally
max_tokens	Hit the max_tokens limit — increase it or use streaming
stop_sequence	Hit a custom stop sequence
tool_use	Claude wants to call a tool — execute it and continue
pause_turn	Model paused and can be resumed (agentic flows)
refusal	Claude refused for safety reasons — output may not match your schema

---

Cost Optimization Strategies

1. Use Prompt Caching for Repeated Context

# Automatic caching (simplest — caches the last cacheable block)
response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    cache_control={"type": "ephemeral"},
    system=large_document_text,  # e.g., 50KB of context
    messages=[{"role": "user", "content": "Summarize the key points"}]
)

# First request: full cost
# Subsequent requests: ~90% cheaper for cached portion

2. Choose the Right Model

# Default to Opus for most tasks
response = client.messages.create(
    model="claude-opus-4-6",  # $5.00/$25.00 per 1M tokens
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain quantum computing"}]
)

# Use Sonnet for high-volume production workloads
standard_response = client.messages.create(
    model="claude-sonnet-4-6",  # $3.00/$15.00 per 1M tokens
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize this document"}]
)

# Use Haiku only for simple, speed-critical tasks
simple_response = client.messages.create(
    model="claude-haiku-4-5",  # $1.00/$5.00 per 1M tokens
    max_tokens=256,
    messages=[{"role": "user", "content": "Classify this as positive or negative"}]
)

3. Use Token Counting Before Requests

count_response = client.messages.count_tokens(
    model="claude-opus-4-6",
    messages=messages,
    system=system
)

estimated_input_cost = count_response.input_tokens * 0.000005  # $5/1M tokens
print(f"Estimated input cost: ${estimated_input_cost:.4f}")

---

Retry with Exponential Backoff

Note: The Anthropic SDK automatically retries rate limit (429) and server errors (5xx) with exponential backoff. You can configure this with max_retries (default: 2). Only implement custom retry logic if you need behavior beyond what the SDK provides.

import time
import random
import anthropic

def call_with_retry(
    client: anthropic.Anthropic,
    max_retries: int = 5,
    base_delay: float = 1.0,
    max_delay: float = 60.0,
    **kwargs
):
    """Call the API with exponential backoff retry."""
    last_exception = None

    for attempt in range(max_retries):
        try:
            return client.messages.create(**kwargs)
        except anthropic.RateLimitError as e:
            last_exception = e
        except anthropic.APIStatusError as e:
            if e.status_code >= 500:
                last_exception = e
            else:
                raise  # Client errors (4xx except 429) should not be retried

        delay = min(base_delay * (2 ** attempt) + random.uniform(0, 1), max_delay)
        print(f"Retry {attempt + 1}/{max_retries} after {delay:.1f}s")
        time.sleep(delay)

    raise last_exception