Anthropic Python API library

Anthropic Python API library

The Anthropic Python library provides convenient access to the Anthropic REST API from any Python 3.9+ application. It includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by httpx.

Documentation

The REST API documentation can be found on docs.anthropic.com. The full API of this library can be found in api.md.

Installation

# install from PyPI
pip install anthropic

Usage

The full API of this library can be found in api.md.

import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ.get("ANTHROPIC_API_KEY"),  # This is the default and can be omitted
)

message = client.messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello, Claude",
        }
    ],
    model="claude-sonnet-4-5-20250929",
)
print(message.content)

While you can provide an api_key keyword argument, we recommend using python-dotenv to add ANTHROPIC_API_KEY="my-anthropic-api-key" to your .env file so that your API Key is not stored in source control.

Async usage

Simply import AsyncAnthropic instead of Anthropic and use await with each API call:

import os
import asyncio
from anthropic import AsyncAnthropic

client = AsyncAnthropic(
    api_key=os.environ.get("ANTHROPIC_API_KEY"),  # This is the default and can be omitted
)


async def main() -> None:
    message = await client.messages.create(
        max_tokens=1024,
        messages=[
            {
                "role": "user",
                "content": "Hello, Claude",
            }
        ],
        model="claude-sonnet-4-5-20250929",
    )
    print(message.content)


asyncio.run(main())

Functionality between the synchronous and asynchronous clients is otherwise identical.

With aiohttp

By default, the async client uses httpx for HTTP requests. However, for improved concurrency performance you may also use aiohttp as the HTTP backend.

You can enable this by installing aiohttp:

# install from PyPI
pip install anthropic[aiohttp]

Then you can enable it by instantiating the client with http_client=DefaultAioHttpClient():

import os
import asyncio
from anthropic import DefaultAioHttpClient
from anthropic import AsyncAnthropic


async def main() -> None:
    async with AsyncAnthropic(
        api_key=os.environ.get("ANTHROPIC_API_KEY"),  # This is the default and can be omitted
        http_client=DefaultAioHttpClient(),
    ) as client:
        message = await client.messages.create(
            max_tokens=1024,
            messages=[
                {
                    "role": "user",
                    "content": "Hello, Claude",
                }
            ],
            model="claude-sonnet-4-5-20250929",
        )
        print(message.content)


asyncio.run(main())

Streaming responses

We provide support for streaming responses using Server Side Events (SSE).

from anthropic import Anthropic

client = Anthropic()

stream = client.messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello, Claude",
        }
    ],
    model="claude-sonnet-4-5-20250929",
    stream=True,
)
for event in stream:
    print(event.type)

The async client uses the exact same interface.

from anthropic import AsyncAnthropic

client = AsyncAnthropic()

stream = await client.messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello, Claude",
        }
    ],
    model="claude-sonnet-4-5-20250929",
    stream=True,
)
async for event in stream:
    print(event.type)

Tool helpers

This library provides helper functions for defining and running tools as pure python functions, for example:

import json
import rich
from typing_extensions import Literal
from anthropic import Anthropic, beta_tool

client = Anthropic()


@beta_tool
def get_weather(location: str) -> str:
    """Lookup the weather for a given city in either celsius or fahrenheit

    Args:
        location: The city and state, e.g. San Francisco, CA
    Returns:
        A dictionary containing the location, temperature, and weather condition.
    """
    # Here you would typically make an API call to a weather service
    # For demonstration, we return a mock response
    return json.dumps(
        {
            "location": location,
            "temperature": "68°F",
            "condition": "Sunny",
        }
    )


runner = client.beta.messages.tool_runner(
    max_tokens=1024,
    model="claude-sonnet-4-5-20250929",
    tools=[get_weather],
    messages=[
        {"role": "user", "content": "What is the weather in SF?"},
    ],
)
for message in runner:
    rich.print(message)

On every iteration, an API request will be made, if Claude wants to call one of the given tools then it will be automatically called, and the result will be returned directly to the model in the next iteration.

For more information see the full docs.

Streaming Helpers

This library provides several conveniences for streaming messages, for example:

import asyncio
from anthropic import AsyncAnthropic

client = AsyncAnthropic()

async def main() -> None:
    async with client.messages.stream(
        max_tokens=1024,
        messages=[
            {
                "role": "user",
                "content": "Say hello there!",
            }
        ],
        model="claude-sonnet-4-5-20250929",
    ) as stream:
        async for text in stream.text_stream:
            print(text, end="", flush=True)
        print()

    message = await stream.get_final_message()
    print(message.to_json())

asyncio.run(main())

Streaming with client.messages.stream(...) exposes various helpers for your convenience including accumulation & SDK-specific events.

Alternatively, you can use client.messages.create(..., stream=True) which only returns an async iterable of the events in the stream and thus uses less memory (it does not build up a final message object for you).

Token counting

To get the token count for a message without creating it you can use the client.messages.count_tokens() method. This takes the same messages list as the .create() method.

count = client.messages.count_tokens(
    model="claude-sonnet-4-5-20250929",
    messages=[
        {"role": "user", "content": "Hello, world"}
    ]
)
count.input_tokens  # 10

You can also see the exact usage for a given request through the usage response property, e.g.

message = client.messages.create(...)
message.usage
# Usage(input_tokens=25, output_tokens=13)

Message Batches

This SDK provides support for the Message Batches API under the client.messages.batches namespace.

Creating a batch

Message Batches take the exact same request params as the standard Messages API:

await client.messages.batches.create(
    requests=[
        {
            "custom_id": "my-first-request",
            "params": {
                "model": "claude-sonnet-4-5-20250929",
                "max_tokens": 1024,
                "messages": [{"role": "user", "content": "Hello, world"}],
            },
        },
        {
            "custom_id": "my-second-request",
            "params": {
                "model": "claude-sonnet-4-5-20250929",
                "max_tokens": 1024,
                "messages": [{"role": "user", "content": "Hi again, friend"}],
            },
        },
    ]
)

Getting results from a batch

Once a Message Batch has been processed, indicated by .processing_status === 'ended', you can access the results with .batches.results()

result_stream = await client.messages.batches.results(batch_id)
async for entry in result_stream:
    if entry.result.type == "succeeded":
        print(entry.result.message.content)

Tool use

This SDK provides support for tool use, aka function calling. More details can be found in the documentation.

AWS Bedrock

This library also provides support for the Anthropic Bedrock API if you install this library with the bedrock extra, e.g. pip install -U anthropic[bedrock].

You can then import and instantiate a separate AnthropicBedrock class, the rest of the API is the same.

from anthropic import AnthropicBedrock

client = AnthropicBedrock()

message = client.messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello!",
        }
    ],
    model="anthropic.claude-sonnet-4-5-20250929-v1:0",
)
print(message)

The bedrock client supports the following arguments for authentication

AnthropicBedrock(
  aws_profile='...',
  aws_region='us-east'
  aws_secret_key='...',
  aws_access_key='...',
  aws_session_token='...',
)

For a more fully fledged example see examples/bedrock.py.

Google Vertex

This library also provides support for the Anthropic Vertex API if you install this library with the vertex extra, e.g. pip install -U anthropic[vertex].

You can then import and instantiate a separate AnthropicVertex/AsyncAnthropicVertex class, which has the same API as the base Anthropic/AsyncAnthropic class.

from anthropic import AnthropicVertex

client = AnthropicVertex()

message = client.messages.create(
    model="claude-sonnet-4@20250514",
    max_tokens=100,
    messages=[
        {
            "role": "user",
            "content": "Hello!",
        }
    ],
)
print(message)

For a more complete example see examples/vertex.py.

Using types

Nested request parameters are TypedDicts. Responses are Pydantic models which also provide helper methods for things like:

• Serializing back into JSON, model.to_json()
• Converting to a dictionary, model.to_dict()

Typed requests and responses provide autocomplete and documentation within your editor. If you would like to see type errors in VS Code to help catch bugs earlier, set python.analysis.typeCheckingMode to basic.

Pagination

List methods in the Anthropic API are paginated.

This library provides auto-paginating iterators with each list response, so you do not have to request successive pages manually:

from anthropic import Anthropic

client = Anthropic()

all_batches = []
# Automatically fetches more pages as needed.
for batch in client.messages.batches.list(
    limit=20,
):
    # Do something with batch here
    all_batches.append(batch)
print(all_batches)

Or, asynchronously:

import asyncio
from anthropic import AsyncAnthropic

client = AsyncAnthropic()


async def main() -> None:
    all_batches = []
    # Iterate through items across all pages, issuing requests as needed.
    async for batch in client.messages.batches.list(
        limit=20,
    ):
        all_batches.append(batch)
    print(all_batches)


asyncio.run(main())

Alternatively, you can use the .has_next_page(), .next_page_info(), or .get_next_page() methods for more granular control working with pages:

first_page = await client.messages.batches.list(
    limit=20,
)
if first_page.has_next_page():
    print(f"will fetch next page using these details: {first_page.next_page_info()}")
    next_page = await first_page.get_next_page()
    print(f"number of items we just fetched: {len(next_page.data)}")

# Remove `await` for non-async usage.

Or just work directly with the returned data:

first_page = await client.messages.batches.list(
    limit=20,
)

print(f"next page cursor: {first_page.last_id}")  # => "next page cursor: ..."
for batch in first_page.data:
    print(batch.id)

# Remove `await` for non-async usage.

Nested params

Nested parameters are dictionaries, typed using TypedDict, for example:

from anthropic import Anthropic

client = Anthropic()

message = client.messages.create(
    max_tokens=1024,
    messages=[
        {
            "content": "Hello, world",
            "role": "user",
        }
    ],
    model="claude-sonnet-4-5-20250929",
    metadata={},
)
print(message.metadata)

File uploads

Request parameters that correspond to file uploads can be passed as bytes, or a PathLike instance or a tuple of (filename, contents, media type).

from pathlib import Path
from anthropic import Anthropic

client = Anthropic()

client.beta.files.upload(
    file=Path("/path/to/file"),
)

The async client uses the exact same interface. If you pass a PathLike instance, the file contents will be read asynchronously automatically.

Handling errors

When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of anthropic.APIConnectionError is raised.

When the API returns a non-success status code (that is, 4xx or 5xx response), a subclass of anthropic.APIStatusError is raised, containing status_code and response properties.

All errors inherit from anthropic.APIError.

import anthropic
from anthropic import Anthropic

client = Anthropic()

try:
    client.messages.create(
        max_tokens=1024,
        messages=[
            {
                "role": "user",
                "content": "Hello, Claude",
            }
        ],
        model="claude-sonnet-4-5-20250929",
    )
except anthropic.APIConnectionError as e:
    print("The server could not be reached")
    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
except anthropic.RateLimitError as e:
    print("A 429 status code was received; we should back off a bit.")
except anthropic.APIStatusError as e:
    print("Another non-200-range status code was received")
    print(e.status_code)
    print(e.response)

Error codes are as follows:

Request IDs

For more information on debugging requests, see these docs

All object responses in the SDK provide a _request_id property which is added from the request-id response header so that you can quickly log failing requests and report them back to Anthropic.

message = client.messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello, Claude",
        }
    ],
    model="claude-sonnet-4-5-20250929",
)
print(message._request_id)  # req_018EeWyXxfu5pfWkrYcMdjWG

Note that unlike other properties that use an _ prefix, the _request_id property is public. Unless documented otherwise, all other _ prefix properties, methods and modules are private.

Retries

Certain errors are automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors are all retried by default.

You can use the max_retries option to configure or disable retry settings:

from anthropic import Anthropic

# Configure the default for all requests:
client = Anthropic(
    # default is 2
    max_retries=0,
)

# Or, configure per-request:
client.with_options(max_retries=5).messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello, Claude",
        }
    ],
    model="claude-sonnet-4-5-20250929",
)

Timeouts

By default requests time out after 10 minutes. You can configure this with a timeout option, which accepts a float or an httpx.Timeout object:

from anthropic import Anthropic

# Configure the default for all requests:
client = Anthropic(
    # 20 seconds (default is 10 minutes)
    timeout=20.0,
)

# More granular control:
client = Anthropic(
    timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
)

# Override per-request:
client.with_options(timeout=5.0).messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello, Claude",
        }
    ],
    model="claude-sonnet-4-5-20250929",
)

On timeout, an APITimeoutError is thrown.

Note that requests that time out are retried twice by default.

Long Requests

[!IMPORTANT] We highly encourage you use the streaming Messages API for longer running requests.

We do not recommend setting a large max_tokens values without using streaming. Some networks may drop idle connections after a certain period of time, which can cause the request to fail or timeout without receiving a response from Anthropic.

This SDK will also throw a ValueError if a non-streaming request is expected to be above roughly 10 minutes long. Passing stream=True or overriding the timeout option at the client or request level disables this error.

An expected request latency longer than the timeout for a non-streaming request will result in the client terminating the connection and retrying without receiving a response.

We set a TCP socket keep-alive option in order to reduce the impact of idle connection timeouts on some networks. This can be overriden by passing a http_client option to the client.

Default Headers

We automatically send the anthropic-version header set to 2023-06-01.

If you need to, you can override it by setting default headers per-request or on the client object.

Be aware that doing so may result in incorrect types and other unexpected or undefined behavior in the SDK.

from anthropic import Anthropic

client = Anthropic(
    default_headers={"anthropic-version": "My-Custom-Value"},
)

Advanced

Logging

We use the standard library logging module.

You can enable logging by setting the environment variable ANTHROPIC_LOG to info.

$ export ANTHROPIC_LOG=info

Or to debug for more verbose logging.

How to tell whether None means null or missing

In an API response, a field may be explicitly null, or missing entirely; in either case, its value is None in this library. You can differentiate the two cases with .model_fields_set:

if response.my_field is None:
  if 'my_field' not in response.model_fields_set:
    print('Got json like {}, without a "my_field" key present at all.')
  else:
    print('Got json like {"my_field": null}.')

Accessing raw response data (e.g. headers)

The "raw" Response object can be accessed by prefixing .with_raw_response. to any HTTP method call, e.g.,

from anthropic import Anthropic

client = Anthropic()
response = client.messages.with_raw_response.create(
    max_tokens=1024,
    messages=[{
        "role": "user",
        "content": "Hello, Claude",
    }],
    model="claude-sonnet-4-5-20250929",
)
print(response.headers.get('X-My-Header'))

message = response.parse()  # get the object that `messages.create()` would have returned
print(message.content)

These methods return a LegacyAPIResponse object. This is a legacy class as we're changing it slightly in the next major version.

For the sync client this will mostly be the same with the exception of content & text will be methods instead of properties. In the async client, all methods will be async.

A migration script will be provided & the migration in general should be smooth.

.with_streaming_response

The above interface eagerly reads the full response body when you make the request, which may not always be what you want.

To stream the response body, use .with_streaming_response instead, which requires a context manager and only reads the response body once you call .read(), .text(), .json(), .iter_bytes(), .iter_text(), .iter_lines() or .parse(). In the async client, these are async methods.

As such, .with_streaming_response methods return a different APIResponse object, and the async client returns an AsyncAPIResponse object.

with client.messages.with_streaming_response.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello, Claude",
        }
    ],
    model="claude-sonnet-4-5-20250929",
) as response:
    print(response.headers.get("X-My-Header"))

    for line in response.iter_lines():
        print(line)

The context manager is required so that the response will reliably be closed.

Making custom/undocumented requests

This library is typed for convenient access to the documented API.

If you need to access undocumented endpoints, params, or response properties, the library can still be used.

Undocumented endpoints

To make requests to undocumented endpoints, you can make requests using client.get, client.post, and other http verbs. Options on the client will be respected (such as retries) when making this request.

import httpx

response = client.post(
    "/foo",
    cast_to=httpx.Response,
    body={"my_param": True},
)

print(response.headers.get("x-foo"))

Undocumented request params

If you want to explicitly send an extra param, you can do so with the extra_query, extra_body, and extra_headers request options.

[!WARNING]

The extra_ parameters of the same name overrides the documented parameters. For security reasons, ensure these methods are only used with trusted input data.

Undocumented response properties

To access undocumented response properties, you can access the extra fields like response.unknown_prop. You can also get all the extra fields on the Pydantic model as a dict with response.model_extra.

Configuring the HTTP client

You can directly override the httpx client to customize it for your use case, including:

• Support for proxies
• Custom transports
• Additional advanced functionality

import httpx
from anthropic import Anthropic, DefaultHttpxClient

client = Anthropic(
    # Or use the `ANTHROPIC_BASE_URL` env var
    base_url="http://my.test.server.example.com:8083",
    http_client=DefaultHttpxClient(
        proxy="http://my.test.proxy.example.com",
        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
    ),
)

You can also customize the client on a per-request basis by using with_options():

client.with_options(http_client=DefaultHttpxClient(...))

Managing HTTP resources

By default the library closes underlying HTTP connections whenever the client is garbage collected. You can manually close the client using the .close() method if desired, or with a context manager that closes when exiting.

from anthropic import Anthropic

with Anthropic() as client:
  # make requests here
  ...

# HTTP client is now closed

Versioning

This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:

1. Changes that only affect static types, without breaking runtime behavior.
2. Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals.)
3. Changes that we do not expect to impact the vast majority of users in practice.

We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.

We are keen for your feedback; please open an issue with questions, bugs, or suggestions.

Determining the installed version

If you've upgraded to the latest version but aren't seeing any new features you were expecting then your python environment is likely still using an older version.

You can determine the version that is being used at runtime with:

import anthropic
print(anthropic.__version__)

Requirements

Python 3.9 or higher.

Contributing

See the contributing documentation.