The async version

Setup

from IPython.display import display,Image

Async SDK

model = models[1]
cli = AsyncAnthropic()
prompt = "I'm Jeremy"
m = mk_msg(prompt)
r = await cli.messages.create(messages=[m], model=model, max_tokens=100)
r

Hi Jeremy! Nice to meet you. How are you doing today? Is there anything I can help you with?

  • id: msg_015XNtKiFEJF4HXdSeSYPtfs
  • content: [{'citations': None, 'text': 'Hi Jeremy! Nice to meet you. How are you doing today? Is there anything I can help you with?', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 10, 'output_tokens': 26, 'server_tool_use': None, 'service_tier': 'standard'}
msgs = mk_msgs([prompt, r, "I forgot my name. Can you remind me please?"]) 
msgs
[{'role': 'user', 'content': "I'm Jeremy"},
 {'role': 'assistant',
  'content': [TextBlock(citations=None, text='Hi Jeremy! Nice to meet you. How are you doing today? Is there anything I can help you with?', type='text')]},
 {'role': 'user', 'content': 'I forgot my name. Can you remind me please?'}]
await cli.messages.create(messages=msgs, model=model, max_tokens=200)

Your name is Jeremy - you introduced yourself to me just a moment ago in your first message!

  • id: msg_01Ar5E7i3k8VZCEeRyD2fiZm
  • content: [{'citations': None, 'text': 'Your name is Jeremy - you introduced yourself to me just a moment ago in your first message!', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 50, 'output_tokens': 22, 'server_tool_use': None, 'service_tier': 'standard'}

source

AsyncClient

 AsyncClient (model, cli=None, log=False, cache=False)

Async Anthropic messages client.

Exported source 
class AsyncClient(Client):
    def __init__(self, model, cli=None, log=False, cache=False):
        "Async Anthropic messages client."
        super().__init__(model,cli,log,cache)
        if not cli: self.c = AsyncAnthropic(default_headers={'anthropic-beta': 'prompt-caching-2024-07-31'})
c = AsyncClient(model)
c._r(r)
c.use
In: 10; Out: 26; Cache create: 0; Cache read: 0; Total Tokens: 36; Search: 0

source

AsyncClient.__call__

 AsyncClient.__call__ (msgs:list, sp='', temp=0, maxtok=4096,
                       maxthinktok=0, prefill='', stream:bool=False,
                       stop=None, tools:Optional[list]=None,
                       tool_choice:Optional[dict]=None, cb=None, cli=None,
                       log=False, cache=False)

Make an async call to Claude.

Type Default Details
msgs list List of messages in the dialog
sp str The system prompt
temp int 0 Temperature
maxtok int 4096 Maximum tokens
maxthinktok int 0 Maximum thinking tokens
prefill str Optional prefill to pass to Claude as start of its response
stream bool False Stream response?
stop NoneType None Stop sequence
tools Optional None List of tools to make available to Claude
tool_choice Optional None Optionally force use of some tool
cb NoneType None Callback to pass result to when complete
cli NoneType None
log bool False
cache bool False
Exported source 
@asave_iter
async def _astream(o, cm, prefill, cb):
    async with cm as s:
        yield prefill
        async for x in s.text_stream: yield x
        o.value = await s.get_final_message()
        await cb(o.value)
Exported source 
@patch
@delegates(Client)
async def __call__(self:AsyncClient,
             msgs:list, # List of messages in the dialog
             sp='', # The system prompt
             temp=0, # Temperature
             maxtok=4096, # Maximum tokens
             maxthinktok=0, # Maximum thinking tokens
             prefill='', # Optional prefill to pass to Claude as start of its response
             stream:bool=False, # Stream response?
             stop=None, # Stop sequence
             tools:Optional[list]=None, # List of tools to make available to Claude
             tool_choice:Optional[dict]=None, # Optionally force use of some tool
             cb=None, # Callback to pass result to when complete
             **kwargs):
    "Make an async call to Claude."
    msgs,kwargs = self._precall(msgs, prefill, sp, temp, maxtok, maxthinktok, stream,
                                stop, tools, tool_choice, kwargs)
    m = self.c.messages
    f = m.stream if stream else m.create
    res = f(model=self.model, messages=msgs, **kwargs)
    async def _cb(v):
        self._log(v, prefill=prefill, msgs=msgs, **kwargs)
        if cb: await cb(v)
    if stream: return _astream(res, prefill, _cb)
    res = await res
    try: return res
    finally: await _cb(res)
c = AsyncClient(model, log=True)
c.use
In: 0; Out: 0; Cache create: 0; Cache read: 0; Total Tokens: 0; Search: 0
c.model = models[1]
await c('Hi')

Hello! How are you doing today? Is there anything I can help you with?

  • id: msg_019u8wbhEBNjkKamuAbZMp7F
  • content: [{'citations': None, 'text': 'Hello! How are you doing today? Is there anything I can help you with?', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 8, 'output_tokens': 20, 'server_tool_use': None, 'service_tier': 'standard'}
c.use
In: 8; Out: 20; Cache create: 0; Cache read: 0; Total Tokens: 28; Search: 0
q = "Very concisely, what is the meaning of life?"
pref = 'According to Douglas Adams,'
await c(q, prefill=pref)

According to Douglas Adams,42. But seriously, there’s no universal answer - it’s deeply personal. Many find meaning through relationships, purpose, growth, helping others, or spiritual beliefs. The search itself might be part of the point.

  • id: msg_0169VpQ8KfSySZzFgoHW7Vf5
  • content: [{'citations': None, 'text': "According to Douglas Adams,42. But seriously, there's no universal answer - it's deeply personal. Many find meaning through relationships, purpose, growth, helping others, or spiritual beliefs. The search itself might be part of the point.", 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 24, 'output_tokens': 46, 'server_tool_use': None, 'service_tier': 'standard'}
c.use
In: 32; Out: 66; Cache create: 0; Cache read: 0; Total Tokens: 98; Search: 0
r = await c(q, prefill=pref, stream=True)
async for o in r: print(o, end='')
r.value
According to Douglas Adams,42. But seriously, there's no universal answer - it's deeply personal. Many find meaning through relationships, purpose, growth, helping others, or spiritual beliefs. The search itself might be part of the point.

According to Douglas Adams,42. But seriously, there’s no universal answer - it’s deeply personal. Many find meaning through relationships, purpose, growth, helping others, or spiritual beliefs. The search itself might be part of the point.

  • id: msg_0157uvVorteH83HXU8mmtSUG
  • content: [{'citations': None, 'text': "According to Douglas Adams,42. But seriously, there's no universal answer - it's deeply personal. Many find meaning through relationships, purpose, growth, helping others, or spiritual beliefs. The search itself might be part of the point.", 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 24, 'output_tokens': 46, 'server_tool_use': None, 'service_tier': 'standard'}
c.use
In: 56; Out: 112; Cache create: 0; Cache read: 0; Total Tokens: 168; Search: 0
def sums(
    a:int,  # First thing to sum
    b:int=1 # Second thing to sum
) -> int: # The sum of the inputs
    "Adds a + b."
    print(f"Finding the sum of {a} and {b}")
    return a + b
a,b = 604542,6458932
pr = f"What is {a}+{b}?"
sp = "You are a summing expert."
tools=[sums]
choice = mk_tool_choice('sums')
choice
{'type': 'tool', 'name': 'sums'}
msgs = mk_msgs(pr)
r = await c(msgs, sp=sp, tools=tools, tool_choice=choice)
r

ToolUseBlock(id=‘toolu_01RSf4W7bXgG3y63muRCNdph’, input={‘a’: 604542, ‘b’: 6458932}, name=‘sums’, type=‘tool_use’)

  • id: msg_014wPskaa9NVZDc6Sny2E4WE
  • content: [{'id': 'toolu_01RSf4W7bXgG3y63muRCNdph', 'input': {'a': 604542, 'b': 6458932}, 'name': 'sums', 'type': 'tool_use'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: tool_use
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 439, 'output_tokens': 57, 'server_tool_use': None, 'service_tier': 'standard'}

source

mk_funcres_async

 mk_funcres_async (fc, ns)

Given tool use block fc, get tool result, and create a tool_result response.

source

mk_toolres_async

 mk_toolres_async (r:collections.abc.Mapping,
                   ns:Optional[collections.abc.Mapping]=None)

Create a tool_result message from response r.

Type Default Details
r Mapping Tool use request response from Claude
ns Optional None Namespace to search for tools 
tr = await mk_toolres_async(r, ns=globals())
tr
Finding the sum of 604542 and 6458932
[{'role': 'assistant',
  'content': [{'id': 'toolu_01RSf4W7bXgG3y63muRCNdph',
    'input': {'a': 604542, 'b': 6458932},
    'name': 'sums',
    'type': 'tool_use'}]},
 {'role': 'user',
  'content': [{'type': 'tool_result',
    'tool_use_id': 'toolu_01RSf4W7bXgG3y63muRCNdph',
    'content': '7063474'}]}]
msgs += tr
r = contents(await c(msgs, sp=sp, tools=sums))
r
'604542 + 6458932 = 7,063,474'

Structured Output

source

AsyncClient.structured

 AsyncClient.structured (msgs:list, tools:Optional[list]=None,
                         ns:Optional[collections.abc.Mapping]=None, sp='',
                         temp=0, maxtok=4096, maxthinktok=0, prefill='',
                         stream:bool=False, stop=None,
                         tool_choice:Optional[dict]=None, cb=None,
                         metadata:MetadataParam|NotGiven=NOT_GIVEN, servic
                         e_tier:"Literal['auto','standard_only']|NotGiven"
                         =NOT_GIVEN,
                         stop_sequences:List[str]|NotGiven=NOT_GIVEN, syst
                         em:Union[str,Iterable[TextBlockParam]]|NotGiven=N
                         OT_GIVEN, temperature:float|NotGiven=NOT_GIVEN,
                         thinking:ThinkingConfigParam|NotGiven=NOT_GIVEN,
                         top_k:int|NotGiven=NOT_GIVEN,
                         top_p:float|NotGiven=NOT_GIVEN,
                         extra_headers:Headers|None=None,
                         extra_query:Query|None=None,
                         extra_body:Body|None=None, timeout:float|httpx.Ti
                         meout|None|NotGiven=NOT_GIVEN)

Return the value of all tool calls (generally used for structured outputs)

Type Default Details
msgs list List of messages in the dialog
tools Optional None List of tools to make available to Claude
ns Optional None Namespace to search for tools
sp str The system prompt
temp int 0 Temperature
maxtok int 4096 Maximum tokens
maxthinktok int 0 Maximum thinking tokens
prefill str Optional prefill to pass to Claude as start of its response
stream bool False Stream response?
stop NoneType None Stop sequence
tool_choice Optional None Optionally force use of some tool
cb NoneType None Callback to pass result to when complete
metadata MetadataParam | NotGiven NOT_GIVEN
service_tier Literal[‘auto’, ‘standard_only’] | NotGiven NOT_GIVEN
stop_sequences List[str] | NotGiven NOT_GIVEN
system Union[str, Iterable[TextBlockParam]] | NotGiven NOT_GIVEN
temperature float | NotGiven NOT_GIVEN
thinking ThinkingConfigParam | NotGiven NOT_GIVEN
top_k int | NotGiven NOT_GIVEN
top_p float | NotGiven NOT_GIVEN
extra_headers Optional None Use the following arguments if you need to pass additional parameters to the API that aren’t available via kwargs.
The extra values given here take precedence over values defined on the client or passed to this method.
extra_query Query | None None
extra_body Body | None None
timeout float | httpx.Timeout | None | NotGiven NOT_GIVEN 
await c.structured(pr, sums)
Finding the sum of 604542 and 6458932
[7063474]
c

ToolUseBlock(id=‘toolu_014Wyt1cQPKDG2x1HuNEm6dq’, input={‘a’: 604542, ‘b’: 6458932}, name=‘sums’, type=‘tool_use’)

Metric Count Cost (USD)
Input tokens 1,451 0.004353
Output tokens 245 0.003675
Cache tokens 0 0.000000
Server tool use 0 0.000000
Total 1,696 $0.008028

AsyncChat

source

AsyncChat

 AsyncChat (model:Optional[str]=None,
            cli:Optional[claudette.core.Client]=None, sp='',
            tools:Optional[list]=None, temp=0, cont_pr:Optional[str]=None,
            cache:bool=False, hist:list=None,
            ns:Optional[collections.abc.Mapping]=None)

Anthropic async chat client.

Type Default Details
model Optional None Model to use (leave empty if passing cli)
cli Optional None Client to use (leave empty if passing model)
sp str
tools Optional None
temp int 0
cont_pr Optional None
cache bool False
hist list None
ns Optional None
Exported source 
@delegates()
class AsyncChat(Chat):
    def __init__(self,
                 model:Optional[str]=None, # Model to use (leave empty if passing `cli`)
                 cli:Optional[Client]=None, # Client to use (leave empty if passing `model`)
                 **kwargs):
        "Anthropic async chat client."
        super().__init__(model, cli, **kwargs)
        if not cli: self.c = AsyncClient(model)
sp = "Always use tools if available, and calculations are requested."
chat = AsyncChat(model, sp=sp)
chat.c.use, chat.h
(In: 0; Out: 0; Cache create: 0; Cache read: 0; Total Tokens: 0; Search: 0, [])

source

AsyncChat.__call__

 AsyncChat.__call__ (pr=None, temp=None, maxtok=4096, maxthinktok=0,
                     stream=False, prefill='',
                     tool_choice:Union[str,bool,dict,NoneType]=None, **kw)

Call self as a function.

Type Default Details
pr NoneType None Prompt / message
temp NoneType None Temperature
maxtok int 4096 Maximum tokens
maxthinktok int 0 Maximum thinking tokens
stream bool False Stream response?
prefill str Optional prefill to pass to Claude as start of its response
tool_choice Union None Optionally force use of some tool
kw VAR_KEYWORD
Exported source 
@patch
async def _append_pr(self:AsyncChat, pr=None):
    prev_role = nested_idx(self.h, -1, 'role') if self.h else 'assistant' # First message should be 'user' if no history
    if pr and prev_role == 'user': await self()
    self._post_pr(pr, prev_role)
Exported source 
@patch
async def __call__(self:AsyncChat,
                   pr=None,  # Prompt / message
                   temp=None, # Temperature
                   maxtok=4096, # Maximum tokens
                   maxthinktok=0, # Maximum thinking tokens
                   stream=False, # Stream response?
                   prefill='', # Optional prefill to pass to Claude as start of its response
                   tool_choice:Optional[Union[str,bool,dict]]=None, # Optionally force use of some tool
                   **kw):
    if temp is None: temp=self.temp
    await self._append_pr(pr)
    async def _cb(v):
        self.last = await mk_toolres_async(v, ns=self.ns)
        self.h += self.last
    return await self.c(self.h, stream=stream, prefill=prefill, sp=self.sp, temp=temp, maxtok=maxtok, maxthinktok=maxthinktok, tools=self.tools, tool_choice=tool_choice, cb=_cb, **kw)
await chat("I'm Jeremy")
await chat("What's my name?")

Your name is Jeremy! You introduced yourself to me at the start of our conversation.

  • id: msg_01Pyu3uCBzVdC4kErLbq2peH
  • content: [{'citations': None, 'text': 'Your name is Jeremy! You introduced yourself to me at the start of our conversation.', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 55, 'output_tokens': 20, 'server_tool_use': None, 'service_tier': 'standard'}
q = "Very concisely, what is the meaning of life?"
pref = 'According to Douglas Adams,'
await chat(q, prefill=pref)

According to Douglas Adams,42. Philosophically, to find purpose, connect with others, and create meaning through your choices and experiences.

  • id: msg_01YQvh7nxU4isTjxnGPhi77s
  • content: [{'citations': None, 'text': 'According to Douglas Adams,42. Philosophically, to find purpose, connect with others, and create meaning through your choices and experiences.', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 95, 'output_tokens': 26, 'server_tool_use': None, 'service_tier': 'standard'}
chat = AsyncChat(model, sp=sp)
r = await chat("I'm Jeremy", stream=True)
async for o in r: print(o, end='')
r.value
Hi Jeremy! Nice to meet you. How are you doing today? Is there anything I can help you with?

Hi Jeremy! Nice to meet you. How are you doing today? Is there anything I can help you with?

  • id: msg_019nc6kTgNmCB5CrPksMPoqJ
  • content: [{'citations': None, 'text': 'Hi Jeremy! Nice to meet you. How are you doing today? Is there anything I can help you with?', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 21, 'output_tokens': 26, 'server_tool_use': None, 'service_tier': 'standard'}
pr = f"What is {a}+{b}?"
chat = AsyncChat(model, sp=sp, tools=[sums])
r = await chat(pr)
r
Finding the sum of 604542 and 6458932

I’ll calculate 604542 + 6458932 for you using the available sum function.

  • id: msg_01P4vF1nhMCocPbnMLYJQrYC
  • content: [{'citations': None, 'text': "I'll calculate 604542 + 6458932 for you using the available sum function.", 'type': 'text'}, {'id': 'toolu_017kjtY3mgsbQ32Khv45PGZG', 'input': {'a': 604542, 'b': 6458932}, 'name': 'sums', 'type': 'tool_use'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: tool_use
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 441, 'output_tokens': 94, 'server_tool_use': None, 'service_tier': 'standard'}
await chat()

The sum of 604542 + 6458932 = 7,063,474.

  • id: msg_01U3weEUEBMngittChXXvEW9
  • content: [{'citations': None, 'text': 'The sum of 604542 + 6458932 = 7,063,474.', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 550, 'output_tokens': 24, 'server_tool_use': None, 'service_tier': 'standard'}
fn = Path('samples/puppy.jpg')
img = fn.read_bytes()
Image(img)

q = "In brief, what color flowers are in this image?"
msg = mk_msg([img, q])
await c([msg])

The flowers in this image are purple.

  • id: msg_01TNWd92J6RYs1QCccodCKH9
  • content: [{'citations': None, 'text': 'The flowers in this image are purple.', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 110, 'output_tokens': 11, 'server_tool_use': None, 'service_tier': 'standard'}

Add cache=True to automatically add to Claude’s KV cache.

chat = AsyncChat(model, sp=sp, cache=True)
await chat("Lorem ipsum dolor sit amet" * 150)

I see you’ve shared a very long string of repeated “Lorem ipsum dolor sit amet” text. Lorem ipsum is commonly used as placeholder text in the printing and typesetting industry.

If you’d like me to help you with something specific regarding this text, I’d be happy to assist! For example, I could:

  • Count how many times the phrase repeats
  • Help you format it differently
  • Replace it with actual content
  • Use it for a specific purpose you have in mind

Is there something particular you’d like me to do with this Lorem ipsum text, or did you have a question or task in mind?

  • id: msg_01PqiRkprKgWUzucSUUgkeSp
  • content: [{'citations': None, 'text': 'I see you\'ve shared a very long string of repeated "Lorem ipsum dolor sit amet" text. Lorem ipsum is commonly used as placeholder text in the printing and typesetting industry.\n\nIf you\'d like me to help you with something specific regarding this text, I\'d be happy to assist! For example, I could:\n\n- Count how many times the phrase repeats\n- Help you format it differently\n- Replace it with actual content\n- Use it for a specific purpose you have in mind\n\nIs there something particular you\'d like me to do with this Lorem ipsum text, or did you have a question or task in mind?', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 1062, 'cache_read_input_tokens': 0, 'input_tokens': 4, 'output_tokens': 133, 'server_tool_use': None, 'service_tier': 'standard'}
chat.use
In: 4; Out: 133; Cache create: 1062; Cache read: 0; Total Tokens: 1199; Search: 0

In this followup call, nearly all the tokens are cached, so the only the new additional tokens are charged at the full rate.

await chat("Whoops, sorry about that!")

No worries at all! That happens to the best of us - copy/paste mishaps are pretty common.

Is there something I can actually help you with today? I’m here and ready to assist with whatever you need!

  • id: msg_01SZAUn8kxJPmCnVcqDmyfTm
  • content: [{'citations': None, 'text': "No worries at all! That happens to the best of us - copy/paste mishaps are pretty common. \n\nIs there something I can actually help you with today? I'm here and ready to assist with whatever you need!", 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 144, 'cache_read_input_tokens': 1062, 'input_tokens': 4, 'output_tokens': 51, 'server_tool_use': None, 'service_tier': 'standard'}
chat.use
In: 8; Out: 184; Cache create: 1206; Cache read: 1062; Total Tokens: 2460; Search: 0

Extended Thinking

Let’s call the model without extended thinking enabled.

chat = AsyncChat(model)
await chat("Write a sentence about Python!")

Python is a versatile, high-level programming language known for its clean syntax and readability, making it popular for everything from web development and data science to artificial intelligence and automation.

  • id: msg_01KFz2yMQdpnWmgcoinnjVNS
  • content: [{'citations': None, 'text': 'Python is a versatile, high-level programming language known for its clean syntax and readability, making it popular for everything from web development and data science to artificial intelligence and automation.', 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 13, 'output_tokens': 40, 'server_tool_use': None, 'service_tier': 'standard'}

Now, let’s call the model with extended thinking enabled.

r = await chat("Write a sentence about Python!", maxthinktok=1024)
r

Python’s extensive ecosystem of libraries and frameworks, combined with its beginner-friendly nature, has made it one of the most widely-used programming languages in both academic research and industry applications.

Thinking The human is asking me to write a sentence about Python again. They might want a different sentence this time, or they might have just repeated the request. I should provide a new sentence about Python that covers different aspects than my previous response.
  • id: msg_01PxDWsEjoCqjRw7GS7AkTNe
  • content: [{'signature': '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', 'thinking': 'The human is asking me to write a sentence about Python again. They might want a different sentence this time, or they might have just repeated the request. I should provide a new sentence about Python that covers different aspects than my previous response.', 'type': 'thinking'}, {'citations': None, 'text': "Python's extensive ecosystem of libraries and frameworks, combined with its beginner-friendly nature, has made it one of the most widely-used programming languages in both academic research and industry applications.", 'type': 'text'}]
  • model: claude-sonnet-4-20250514
  • role: assistant
  • stop_reason: end_turn
  • stop_sequence: None
  • type: message
  • usage: {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 90, 'output_tokens': 98, 'server_tool_use': None, 'service_tier': 'standard'}
r.content
[ThinkingBlock(signature='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', thinking='The human is asking me to write a sentence about Python again. They might want a different sentence this time, or they might have just repeated the request. I should provide a new sentence about Python that covers different aspects than my previous response.', type='thinking'),
 TextBlock(citations=None, text="Python's extensive ecosystem of libraries and frameworks, combined with its beginner-friendly nature, has made it one of the most widely-used programming languages in both academic research and industry applications.", type='text')]