messages.py

# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.

from __future__ import annotations

from typing import List, Union, Iterable
from functools import partial
from itertools import chain
from typing_extensions import Literal, overload

import httpx

from .... import _legacy_response
from ...._types import NOT_GIVEN, Body, Query, Headers, NotGiven
from ...._utils import (
    is_given,
    required_args,
    maybe_transform,
    strip_not_given,
    async_maybe_transform,
)
from ...._compat import cached_property
from ...._resource import SyncAPIResource, AsyncAPIResource
from ...._response import to_streamed_response_wrapper, async_to_streamed_response_wrapper
from ...._constants import DEFAULT_TIMEOUT
from ...._streaming import Stream, AsyncStream
from ...._base_client import make_request_options
from ....lib.streaming import PromptCachingBetaMessageStreamManager, AsyncPromptCachingBetaMessageStreamManager
from ....types.model_param import ModelParam
from ....types.metadata_param import MetadataParam
from ....types.tool_choice_param import ToolChoiceParam
from ....types.beta.prompt_caching import message_create_params
from ....types.anthropic_beta_param import AnthropicBetaParam
from ....types.beta.prompt_caching.prompt_caching_beta_message import PromptCachingBetaMessage
from ....types.beta.prompt_caching.prompt_caching_beta_tool_param import PromptCachingBetaToolParam
from ....types.beta.prompt_caching.prompt_caching_beta_message_param import PromptCachingBetaMessageParam
from ....types.beta.prompt_caching.prompt_caching_beta_text_block_param import PromptCachingBetaTextBlockParam
from ....types.beta.prompt_caching.raw_prompt_caching_beta_message_stream_event import (
    RawPromptCachingBetaMessageStreamEvent,
)

__all__ = ["Messages", "AsyncMessages"]


class Messages(SyncAPIResource):
    @cached_property
    def with_raw_response(self) -> MessagesWithRawResponse:
        """
        This property can be used as a prefix for any HTTP method call to return the
        the raw response object instead of the parsed content.

        For more information, see https://www.github.com/anthropics/anthropic-sdk-python#accessing-raw-response-data-eg-headers
        """
        return MessagesWithRawResponse(self)

    @cached_property
    def with_streaming_response(self) -> MessagesWithStreamingResponse:
        """
        An alternative to `.with_raw_response` that doesn't eagerly read the response body.

        For more information, see https://www.github.com/anthropics/anthropic-sdk-python#with_streaming_response
        """
        return MessagesWithStreamingResponse(self)

    @overload
    def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        stream: Literal[False] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> PromptCachingBetaMessage:
        """
        Send a structured list of input messages with text and/or image content, and the
        model will generate the next message in the conversation.

        The Messages API can be used for either single queries or stateless multi-turn
        conversations.

        Args:
          max_tokens: The maximum number of tokens to generate before stopping.

              Note that our models may stop _before_ reaching this maximum. This parameter
              only specifies the absolute maximum number of tokens to generate.

              Different models have different maximum values for this parameter. See
              [models](https://docs.anthropic.com/en/docs/models-overview) for details.

          messages: Input messages.

              Our models are trained to operate on alternating `user` and `assistant`
              conversational turns. When creating a new `Message`, you specify the prior
              conversational turns with the `messages` parameter, and the model then generates
              the next `Message` in the conversation. Consecutive `user` or `assistant` turns
              in your request will be combined into a single turn.

              Each input message must be an object with a `role` and `content`. You can
              specify a single `user`-role message, or you can include multiple `user` and
              `assistant` messages.

              If the final message uses the `assistant` role, the response content will
              continue immediately from the content in that message. This can be used to
              constrain part of the model's response.

              Example with a single `user` message:

              ```json
              [{ "role": "user", "content": "Hello, Claude" }]
              ```

              Example with multiple conversational turns:

              ```json
              [
                { "role": "user", "content": "Hello there." },
                { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
                { "role": "user", "content": "Can you explain LLMs in plain English?" }
              ]
              ```

              Example with a partially-filled response from Claude:

              ```json
              [
                {
                  "role": "user",
                  "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
                },
                { "role": "assistant", "content": "The best answer is (" }
              ]
              ```

              Each input message `content` may be either a single `string` or an array of
              content blocks, where each block has a specific `type`. Using a `string` for
              `content` is shorthand for an array of one content block of type `"text"`. The
              following input messages are equivalent:

              ```json
              { "role": "user", "content": "Hello, Claude" }
              ```

              ```json
              { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
              ```

              Starting with Claude 3 models, you can also send image content blocks:

              ```json
              {
                "role": "user",
                "content": [
                  {
                    "type": "image",
                    "source": {
                      "type": "base64",
                      "media_type": "image/jpeg",
                      "data": "/9j/4AAQSkZJRg..."
                    }
                  },
                  { "type": "text", "text": "What is in this image?" }
                ]
              }
              ```

              We currently support the `base64` source type for images, and the `image/jpeg`,
              `image/png`, `image/gif`, and `image/webp` media types.

              See [examples](https://docs.anthropic.com/en/api/messages-examples#vision) for
              more input examples.

              Note that if you want to include a
              [system prompt](https://docs.anthropic.com/en/docs/system-prompts), you can use
              the top-level `system` parameter — there is no `"system"` role for input
              messages in the Messages API.

          model: The model that will complete your prompt.\n\nSee
              [models](https://docs.anthropic.com/en/docs/models-overview) for additional
              details and options.

          metadata: An object describing metadata about the request.

          stop_sequences: Custom text sequences that will cause the model to stop generating.

              Our models will normally stop when they have naturally completed their turn,
              which will result in a response `stop_reason` of `"end_turn"`.

              If you want the model to stop generating when it encounters custom strings of
              text, you can use the `stop_sequences` parameter. If the model encounters one of
              the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
              and the response `stop_sequence` value will contain the matched stop sequence.

          stream: Whether to incrementally stream the response using server-sent events.

              See [streaming](https://docs.anthropic.com/en/api/messages-streaming) for
              details.

          system: System prompt.

              A system prompt is a way of providing context and instructions to Claude, such
              as specifying a particular goal or role. See our
              [guide to system prompts](https://docs.anthropic.com/en/docs/system-prompts).

          temperature: Amount of randomness injected into the response.

              Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
              for analytical / multiple choice, and closer to `1.0` for creative and
              generative tasks.

              Note that even with `temperature` of `0.0`, the results will not be fully
              deterministic.

          tool_choice: How the model should use the provided tools. The model can use a specific tool,
              any available tool, or decide by itself.

          tools: Definitions of tools that the model may use.

              If you include `tools` in your API request, the model may return `tool_use`
              content blocks that represent the model's use of those tools. You can then run
              those tools using the tool input generated by the model and then optionally
              return results back to the model using `tool_result` content blocks.

              Each tool definition includes:

              - `name`: Name of the tool.
              - `description`: Optional, but strongly-recommended description of the tool.
              - `input_schema`: [JSON schema](https://json-schema.org/) for the tool `input`
                shape that the model will produce in `tool_use` output content blocks.

              For example, if you defined `tools` as:

              ```json
              [
                {
                  "name": "get_stock_price",
                  "description": "Get the current stock price for a given ticker symbol.",
                  "input_schema": {
                    "type": "object",
                    "properties": {
                      "ticker": {
                        "type": "string",
                        "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
                      }
                    },
                    "required": ["ticker"]
                  }
                }
              ]
              ```

              And then asked the model "What's the S&P 500 at today?", the model might produce
              `tool_use` content blocks in the response like this:

              ```json
              [
                {
                  "type": "tool_use",
                  "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "name": "get_stock_price",
                  "input": { "ticker": "^GSPC" }
                }
              ]
              ```

              You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an
              input, and return the following back to the model in a subsequent `user`
              message:

              ```json
              [
                {
                  "type": "tool_result",
                  "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "content": "259.75 USD"
                }
              ]
              ```

              Tools can be used for workflows that include running client-side tools and
              functions, or more generally whenever you want the model to produce a particular
              JSON structure of output.

              See our [guide](https://docs.anthropic.com/en/docs/tool-use) for more details.

          top_k: Only sample from the top K options for each subsequent token.

              Used to remove "long tail" low probability responses.
              [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          top_p: Use nucleus sampling.

              In nucleus sampling, we compute the cumulative distribution over all the options
              for each subsequent token in decreasing probability order and cut it off once it
              reaches a particular probability specified by `top_p`. You should either alter
              `temperature` or `top_p`, but not both.

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          betas: Optional header to specify the beta version(s) you want to use.

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        ...

    @overload
    def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        stream: Literal[True],
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> Stream[RawPromptCachingBetaMessageStreamEvent]:
        """
        Send a structured list of input messages with text and/or image content, and the
        model will generate the next message in the conversation.

        The Messages API can be used for either single queries or stateless multi-turn
        conversations.

        Args:
          max_tokens: The maximum number of tokens to generate before stopping.

              Note that our models may stop _before_ reaching this maximum. This parameter
              only specifies the absolute maximum number of tokens to generate.

              Different models have different maximum values for this parameter. See
              [models](https://docs.anthropic.com/en/docs/models-overview) for details.

          messages: Input messages.

              Our models are trained to operate on alternating `user` and `assistant`
              conversational turns. When creating a new `Message`, you specify the prior
              conversational turns with the `messages` parameter, and the model then generates
              the next `Message` in the conversation. Consecutive `user` or `assistant` turns
              in your request will be combined into a single turn.

              Each input message must be an object with a `role` and `content`. You can
              specify a single `user`-role message, or you can include multiple `user` and
              `assistant` messages.

              If the final message uses the `assistant` role, the response content will
              continue immediately from the content in that message. This can be used to
              constrain part of the model's response.

              Example with a single `user` message:

              ```json
              [{ "role": "user", "content": "Hello, Claude" }]
              ```

              Example with multiple conversational turns:

              ```json
              [
                { "role": "user", "content": "Hello there." },
                { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
                { "role": "user", "content": "Can you explain LLMs in plain English?" }
              ]
              ```

              Example with a partially-filled response from Claude:

              ```json
              [
                {
                  "role": "user",
                  "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
                },
                { "role": "assistant", "content": "The best answer is (" }
              ]
              ```

              Each input message `content` may be either a single `string` or an array of
              content blocks, where each block has a specific `type`. Using a `string` for
              `content` is shorthand for an array of one content block of type `"text"`. The
              following input messages are equivalent:

              ```json
              { "role": "user", "content": "Hello, Claude" }
              ```

              ```json
              { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
              ```

              Starting with Claude 3 models, you can also send image content blocks:

              ```json
              {
                "role": "user",
                "content": [
                  {
                    "type": "image",
                    "source": {
                      "type": "base64",
                      "media_type": "image/jpeg",
                      "data": "/9j/4AAQSkZJRg..."
                    }
                  },
                  { "type": "text", "text": "What is in this image?" }
                ]
              }
              ```

              We currently support the `base64` source type for images, and the `image/jpeg`,
              `image/png`, `image/gif`, and `image/webp` media types.

              See [examples](https://docs.anthropic.com/en/api/messages-examples#vision) for
              more input examples.

              Note that if you want to include a
              [system prompt](https://docs.anthropic.com/en/docs/system-prompts), you can use
              the top-level `system` parameter — there is no `"system"` role for input
              messages in the Messages API.

          model: The model that will complete your prompt.\n\nSee
              [models](https://docs.anthropic.com/en/docs/models-overview) for additional
              details and options.

          stream: Whether to incrementally stream the response using server-sent events.

              See [streaming](https://docs.anthropic.com/en/api/messages-streaming) for
              details.

          metadata: An object describing metadata about the request.

          stop_sequences: Custom text sequences that will cause the model to stop generating.

              Our models will normally stop when they have naturally completed their turn,
              which will result in a response `stop_reason` of `"end_turn"`.

              If you want the model to stop generating when it encounters custom strings of
              text, you can use the `stop_sequences` parameter. If the model encounters one of
              the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
              and the response `stop_sequence` value will contain the matched stop sequence.

          system: System prompt.

              A system prompt is a way of providing context and instructions to Claude, such
              as specifying a particular goal or role. See our
              [guide to system prompts](https://docs.anthropic.com/en/docs/system-prompts).

          temperature: Amount of randomness injected into the response.

              Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
              for analytical / multiple choice, and closer to `1.0` for creative and
              generative tasks.

              Note that even with `temperature` of `0.0`, the results will not be fully
              deterministic.

          tool_choice: How the model should use the provided tools. The model can use a specific tool,
              any available tool, or decide by itself.

          tools: Definitions of tools that the model may use.

              If you include `tools` in your API request, the model may return `tool_use`
              content blocks that represent the model's use of those tools. You can then run
              those tools using the tool input generated by the model and then optionally
              return results back to the model using `tool_result` content blocks.

              Each tool definition includes:

              - `name`: Name of the tool.
              - `description`: Optional, but strongly-recommended description of the tool.
              - `input_schema`: [JSON schema](https://json-schema.org/) for the tool `input`
                shape that the model will produce in `tool_use` output content blocks.

              For example, if you defined `tools` as:

              ```json
              [
                {
                  "name": "get_stock_price",
                  "description": "Get the current stock price for a given ticker symbol.",
                  "input_schema": {
                    "type": "object",
                    "properties": {
                      "ticker": {
                        "type": "string",
                        "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
                      }
                    },
                    "required": ["ticker"]
                  }
                }
              ]
              ```

              And then asked the model "What's the S&P 500 at today?", the model might produce
              `tool_use` content blocks in the response like this:

              ```json
              [
                {
                  "type": "tool_use",
                  "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "name": "get_stock_price",
                  "input": { "ticker": "^GSPC" }
                }
              ]
              ```

              You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an
              input, and return the following back to the model in a subsequent `user`
              message:

              ```json
              [
                {
                  "type": "tool_result",
                  "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "content": "259.75 USD"
                }
              ]
              ```

              Tools can be used for workflows that include running client-side tools and
              functions, or more generally whenever you want the model to produce a particular
              JSON structure of output.

              See our [guide](https://docs.anthropic.com/en/docs/tool-use) for more details.

          top_k: Only sample from the top K options for each subsequent token.

              Used to remove "long tail" low probability responses.
              [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          top_p: Use nucleus sampling.

              In nucleus sampling, we compute the cumulative distribution over all the options
              for each subsequent token in decreasing probability order and cut it off once it
              reaches a particular probability specified by `top_p`. You should either alter
              `temperature` or `top_p`, but not both.

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          betas: Optional header to specify the beta version(s) you want to use.

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        ...

    @overload
    def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        stream: bool,
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> PromptCachingBetaMessage | Stream[RawPromptCachingBetaMessageStreamEvent]:
        """
        Send a structured list of input messages with text and/or image content, and the
        model will generate the next message in the conversation.

        The Messages API can be used for either single queries or stateless multi-turn
        conversations.

        Args:
          max_tokens: The maximum number of tokens to generate before stopping.

              Note that our models may stop _before_ reaching this maximum. This parameter
              only specifies the absolute maximum number of tokens to generate.

              Different models have different maximum values for this parameter. See
              [models](https://docs.anthropic.com/en/docs/models-overview) for details.

          messages: Input messages.

              Our models are trained to operate on alternating `user` and `assistant`
              conversational turns. When creating a new `Message`, you specify the prior
              conversational turns with the `messages` parameter, and the model then generates
              the next `Message` in the conversation. Consecutive `user` or `assistant` turns
              in your request will be combined into a single turn.

              Each input message must be an object with a `role` and `content`. You can
              specify a single `user`-role message, or you can include multiple `user` and
              `assistant` messages.

              If the final message uses the `assistant` role, the response content will
              continue immediately from the content in that message. This can be used to
              constrain part of the model's response.

              Example with a single `user` message:

              ```json
              [{ "role": "user", "content": "Hello, Claude" }]
              ```

              Example with multiple conversational turns:

              ```json
              [
                { "role": "user", "content": "Hello there." },
                { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
                { "role": "user", "content": "Can you explain LLMs in plain English?" }
              ]
              ```

              Example with a partially-filled response from Claude:

              ```json
              [
                {
                  "role": "user",
                  "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
                },
                { "role": "assistant", "content": "The best answer is (" }
              ]
              ```

              Each input message `content` may be either a single `string` or an array of
              content blocks, where each block has a specific `type`. Using a `string` for
              `content` is shorthand for an array of one content block of type `"text"`. The
              following input messages are equivalent:

              ```json
              { "role": "user", "content": "Hello, Claude" }
              ```

              ```json
              { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
              ```

              Starting with Claude 3 models, you can also send image content blocks:

              ```json
              {
                "role": "user",
                "content": [
                  {
                    "type": "image",
                    "source": {
                      "type": "base64",
                      "media_type": "image/jpeg",
                      "data": "/9j/4AAQSkZJRg..."
                    }
                  },
                  { "type": "text", "text": "What is in this image?" }
                ]
              }
              ```

              We currently support the `base64` source type for images, and the `image/jpeg`,
              `image/png`, `image/gif`, and `image/webp` media types.

              See [examples](https://docs.anthropic.com/en/api/messages-examples#vision) for
              more input examples.

              Note that if you want to include a
              [system prompt](https://docs.anthropic.com/en/docs/system-prompts), you can use
              the top-level `system` parameter — there is no `"system"` role for input
              messages in the Messages API.

          model: The model that will complete your prompt.\n\nSee
              [models](https://docs.anthropic.com/en/docs/models-overview) for additional
              details and options.

          stream: Whether to incrementally stream the response using server-sent events.

              See [streaming](https://docs.anthropic.com/en/api/messages-streaming) for
              details.

          metadata: An object describing metadata about the request.

          stop_sequences: Custom text sequences that will cause the model to stop generating.

              Our models will normally stop when they have naturally completed their turn,
              which will result in a response `stop_reason` of `"end_turn"`.

              If you want the model to stop generating when it encounters custom strings of
              text, you can use the `stop_sequences` parameter. If the model encounters one of
              the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
              and the response `stop_sequence` value will contain the matched stop sequence.

          system: System prompt.

              A system prompt is a way of providing context and instructions to Claude, such
              as specifying a particular goal or role. See our
              [guide to system prompts](https://docs.anthropic.com/en/docs/system-prompts).

          temperature: Amount of randomness injected into the response.

              Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
              for analytical / multiple choice, and closer to `1.0` for creative and
              generative tasks.

              Note that even with `temperature` of `0.0`, the results will not be fully
              deterministic.

          tool_choice: How the model should use the provided tools. The model can use a specific tool,
              any available tool, or decide by itself.

          tools: Definitions of tools that the model may use.

              If you include `tools` in your API request, the model may return `tool_use`
              content blocks that represent the model's use of those tools. You can then run
              those tools using the tool input generated by the model and then optionally
              return results back to the model using `tool_result` content blocks.

              Each tool definition includes:

              - `name`: Name of the tool.
              - `description`: Optional, but strongly-recommended description of the tool.
              - `input_schema`: [JSON schema](https://json-schema.org/) for the tool `input`
                shape that the model will produce in `tool_use` output content blocks.

              For example, if you defined `tools` as:

              ```json
              [
                {
                  "name": "get_stock_price",
                  "description": "Get the current stock price for a given ticker symbol.",
                  "input_schema": {
                    "type": "object",
                    "properties": {
                      "ticker": {
                        "type": "string",
                        "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
                      }
                    },
                    "required": ["ticker"]
                  }
                }
              ]
              ```

              And then asked the model "What's the S&P 500 at today?", the model might produce
              `tool_use` content blocks in the response like this:

              ```json
              [
                {
                  "type": "tool_use",
                  "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "name": "get_stock_price",
                  "input": { "ticker": "^GSPC" }
                }
              ]
              ```

              You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an
              input, and return the following back to the model in a subsequent `user`
              message:

              ```json
              [
                {
                  "type": "tool_result",
                  "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "content": "259.75 USD"
                }
              ]
              ```

              Tools can be used for workflows that include running client-side tools and
              functions, or more generally whenever you want the model to produce a particular
              JSON structure of output.

              See our [guide](https://docs.anthropic.com/en/docs/tool-use) for more details.

          top_k: Only sample from the top K options for each subsequent token.

              Used to remove "long tail" low probability responses.
              [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          top_p: Use nucleus sampling.

              In nucleus sampling, we compute the cumulative distribution over all the options
              for each subsequent token in decreasing probability order and cut it off once it
              reaches a particular probability specified by `top_p`. You should either alter
              `temperature` or `top_p`, but not both.

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          betas: Optional header to specify the beta version(s) you want to use.

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        ...

    @required_args(["max_tokens", "messages", "model"], ["max_tokens", "messages", "model", "stream"])
    def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        stream: Literal[False] | Literal[True] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> PromptCachingBetaMessage | Stream[RawPromptCachingBetaMessageStreamEvent]:
        if not is_given(timeout) and self._client.timeout == DEFAULT_TIMEOUT:
            timeout = 600
        extra_headers = {
            **strip_not_given(
                {
                    "anthropic-beta": ",".join(chain((str(e) for e in betas), ["prompt-caching-2024-07-31"]))
                    if is_given(betas)
                    else NOT_GIVEN
                }
            ),
            **(extra_headers or {}),
        }
        extra_headers = {"anthropic-beta": "prompt-caching-2024-07-31", **(extra_headers or {})}
        return self._post(
            "/v1/messages?beta=prompt_caching",
            body=maybe_transform(
                {
                    "max_tokens": max_tokens,
                    "messages": messages,
                    "model": model,
                    "metadata": metadata,
                    "stop_sequences": stop_sequences,
                    "stream": stream,
                    "system": system,
                    "temperature": temperature,
                    "tool_choice": tool_choice,
                    "tools": tools,
                    "top_k": top_k,
                    "top_p": top_p,
                },
                message_create_params.MessageCreateParams,
            ),
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=PromptCachingBetaMessage,
            stream=stream or False,
            stream_cls=Stream[RawPromptCachingBetaMessageStreamEvent],
        )

    def stream(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        metadata: message_create_params.Metadata | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: message_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> PromptCachingBetaMessageStreamManager:
        """Create a Message stream"""
        if not is_given(timeout) and self._client.timeout == DEFAULT_TIMEOUT:
            timeout = 600

        extra_headers = {
            "anthropic-beta": "prompt-caching-2024-07-31",
            "X-Stainless-Stream-Helper": "beta.prompt_caching.messages",
            **(extra_headers or {}),
        }
        request = partial(
            self._post,
            "/v1/messages?beta=prompt_caching",
            body=maybe_transform(
                {
                    "max_tokens": max_tokens,
                    "messages": messages,
                    "model": model,
                    "metadata": metadata,
                    "stop_sequences": stop_sequences,
                    "stream": True,
                    "system": system,
                    "temperature": temperature,
                    "tool_choice": tool_choice,
                    "tools": tools,
                    "top_k": top_k,
                    "top_p": top_p,
                },
                message_create_params.MessageCreateParams,
            ),
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=PromptCachingBetaMessage,
            stream=True,
            stream_cls=Stream[RawPromptCachingBetaMessageStreamEvent],
        )
        return PromptCachingBetaMessageStreamManager(request)


class AsyncMessages(AsyncAPIResource):
    @cached_property
    def with_raw_response(self) -> AsyncMessagesWithRawResponse:
        """
        This property can be used as a prefix for any HTTP method call to return the
        the raw response object instead of the parsed content.

        For more information, see https://www.github.com/anthropics/anthropic-sdk-python#accessing-raw-response-data-eg-headers
        """
        return AsyncMessagesWithRawResponse(self)

    @cached_property
    def with_streaming_response(self) -> AsyncMessagesWithStreamingResponse:
        """
        An alternative to `.with_raw_response` that doesn't eagerly read the response body.

        For more information, see https://www.github.com/anthropics/anthropic-sdk-python#with_streaming_response
        """
        return AsyncMessagesWithStreamingResponse(self)

    @overload
    async def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        stream: Literal[False] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> PromptCachingBetaMessage:
        """
        Send a structured list of input messages with text and/or image content, and the
        model will generate the next message in the conversation.

        The Messages API can be used for either single queries or stateless multi-turn
        conversations.

        Args:
          max_tokens: The maximum number of tokens to generate before stopping.

              Note that our models may stop _before_ reaching this maximum. This parameter
              only specifies the absolute maximum number of tokens to generate.

              Different models have different maximum values for this parameter. See
              [models](https://docs.anthropic.com/en/docs/models-overview) for details.

          messages: Input messages.

              Our models are trained to operate on alternating `user` and `assistant`
              conversational turns. When creating a new `Message`, you specify the prior
              conversational turns with the `messages` parameter, and the model then generates
              the next `Message` in the conversation. Consecutive `user` or `assistant` turns
              in your request will be combined into a single turn.

              Each input message must be an object with a `role` and `content`. You can
              specify a single `user`-role message, or you can include multiple `user` and
              `assistant` messages.

              If the final message uses the `assistant` role, the response content will
              continue immediately from the content in that message. This can be used to
              constrain part of the model's response.

              Example with a single `user` message:

              ```json
              [{ "role": "user", "content": "Hello, Claude" }]
              ```

              Example with multiple conversational turns:

              ```json
              [
                { "role": "user", "content": "Hello there." },
                { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
                { "role": "user", "content": "Can you explain LLMs in plain English?" }
              ]
              ```

              Example with a partially-filled response from Claude:

              ```json
              [
                {
                  "role": "user",
                  "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
                },
                { "role": "assistant", "content": "The best answer is (" }
              ]
              ```

              Each input message `content` may be either a single `string` or an array of
              content blocks, where each block has a specific `type`. Using a `string` for
              `content` is shorthand for an array of one content block of type `"text"`. The
              following input messages are equivalent:

              ```json
              { "role": "user", "content": "Hello, Claude" }
              ```

              ```json
              { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
              ```

              Starting with Claude 3 models, you can also send image content blocks:

              ```json
              {
                "role": "user",
                "content": [
                  {
                    "type": "image",
                    "source": {
                      "type": "base64",
                      "media_type": "image/jpeg",
                      "data": "/9j/4AAQSkZJRg..."
                    }
                  },
                  { "type": "text", "text": "What is in this image?" }
                ]
              }
              ```

              We currently support the `base64` source type for images, and the `image/jpeg`,
              `image/png`, `image/gif`, and `image/webp` media types.

              See [examples](https://docs.anthropic.com/en/api/messages-examples#vision) for
              more input examples.

              Note that if you want to include a
              [system prompt](https://docs.anthropic.com/en/docs/system-prompts), you can use
              the top-level `system` parameter — there is no `"system"` role for input
              messages in the Messages API.

          model: The model that will complete your prompt.\n\nSee
              [models](https://docs.anthropic.com/en/docs/models-overview) for additional
              details and options.

          metadata: An object describing metadata about the request.

          stop_sequences: Custom text sequences that will cause the model to stop generating.

              Our models will normally stop when they have naturally completed their turn,
              which will result in a response `stop_reason` of `"end_turn"`.

              If you want the model to stop generating when it encounters custom strings of
              text, you can use the `stop_sequences` parameter. If the model encounters one of
              the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
              and the response `stop_sequence` value will contain the matched stop sequence.

          stream: Whether to incrementally stream the response using server-sent events.

              See [streaming](https://docs.anthropic.com/en/api/messages-streaming) for
              details.

          system: System prompt.

              A system prompt is a way of providing context and instructions to Claude, such
              as specifying a particular goal or role. See our
              [guide to system prompts](https://docs.anthropic.com/en/docs/system-prompts).

          temperature: Amount of randomness injected into the response.

              Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
              for analytical / multiple choice, and closer to `1.0` for creative and
              generative tasks.

              Note that even with `temperature` of `0.0`, the results will not be fully
              deterministic.

          tool_choice: How the model should use the provided tools. The model can use a specific tool,
              any available tool, or decide by itself.

          tools: Definitions of tools that the model may use.

              If you include `tools` in your API request, the model may return `tool_use`
              content blocks that represent the model's use of those tools. You can then run
              those tools using the tool input generated by the model and then optionally
              return results back to the model using `tool_result` content blocks.

              Each tool definition includes:

              - `name`: Name of the tool.
              - `description`: Optional, but strongly-recommended description of the tool.
              - `input_schema`: [JSON schema](https://json-schema.org/) for the tool `input`
                shape that the model will produce in `tool_use` output content blocks.

              For example, if you defined `tools` as:

              ```json
              [
                {
                  "name": "get_stock_price",
                  "description": "Get the current stock price for a given ticker symbol.",
                  "input_schema": {
                    "type": "object",
                    "properties": {
                      "ticker": {
                        "type": "string",
                        "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
                      }
                    },
                    "required": ["ticker"]
                  }
                }
              ]
              ```

              And then asked the model "What's the S&P 500 at today?", the model might produce
              `tool_use` content blocks in the response like this:

              ```json
              [
                {
                  "type": "tool_use",
                  "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "name": "get_stock_price",
                  "input": { "ticker": "^GSPC" }
                }
              ]
              ```

              You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an
              input, and return the following back to the model in a subsequent `user`
              message:

              ```json
              [
                {
                  "type": "tool_result",
                  "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "content": "259.75 USD"
                }
              ]
              ```

              Tools can be used for workflows that include running client-side tools and
              functions, or more generally whenever you want the model to produce a particular
              JSON structure of output.

              See our [guide](https://docs.anthropic.com/en/docs/tool-use) for more details.

          top_k: Only sample from the top K options for each subsequent token.

              Used to remove "long tail" low probability responses.
              [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          top_p: Use nucleus sampling.

              In nucleus sampling, we compute the cumulative distribution over all the options
              for each subsequent token in decreasing probability order and cut it off once it
              reaches a particular probability specified by `top_p`. You should either alter
              `temperature` or `top_p`, but not both.

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          betas: Optional header to specify the beta version(s) you want to use.

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        ...

    @overload
    async def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        stream: Literal[True],
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> AsyncStream[RawPromptCachingBetaMessageStreamEvent]:
        """
        Send a structured list of input messages with text and/or image content, and the
        model will generate the next message in the conversation.

        The Messages API can be used for either single queries or stateless multi-turn
        conversations.

        Args:
          max_tokens: The maximum number of tokens to generate before stopping.

              Note that our models may stop _before_ reaching this maximum. This parameter
              only specifies the absolute maximum number of tokens to generate.

              Different models have different maximum values for this parameter. See
              [models](https://docs.anthropic.com/en/docs/models-overview) for details.

          messages: Input messages.

              Our models are trained to operate on alternating `user` and `assistant`
              conversational turns. When creating a new `Message`, you specify the prior
              conversational turns with the `messages` parameter, and the model then generates
              the next `Message` in the conversation. Consecutive `user` or `assistant` turns
              in your request will be combined into a single turn.

              Each input message must be an object with a `role` and `content`. You can
              specify a single `user`-role message, or you can include multiple `user` and
              `assistant` messages.

              If the final message uses the `assistant` role, the response content will
              continue immediately from the content in that message. This can be used to
              constrain part of the model's response.

              Example with a single `user` message:

              ```json
              [{ "role": "user", "content": "Hello, Claude" }]
              ```

              Example with multiple conversational turns:

              ```json
              [
                { "role": "user", "content": "Hello there." },
                { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
                { "role": "user", "content": "Can you explain LLMs in plain English?" }
              ]
              ```

              Example with a partially-filled response from Claude:

              ```json
              [
                {
                  "role": "user",
                  "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
                },
                { "role": "assistant", "content": "The best answer is (" }
              ]
              ```

              Each input message `content` may be either a single `string` or an array of
              content blocks, where each block has a specific `type`. Using a `string` for
              `content` is shorthand for an array of one content block of type `"text"`. The
              following input messages are equivalent:

              ```json
              { "role": "user", "content": "Hello, Claude" }
              ```

              ```json
              { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
              ```

              Starting with Claude 3 models, you can also send image content blocks:

              ```json
              {
                "role": "user",
                "content": [
                  {
                    "type": "image",
                    "source": {
                      "type": "base64",
                      "media_type": "image/jpeg",
                      "data": "/9j/4AAQSkZJRg..."
                    }
                  },
                  { "type": "text", "text": "What is in this image?" }
                ]
              }
              ```

              We currently support the `base64` source type for images, and the `image/jpeg`,
              `image/png`, `image/gif`, and `image/webp` media types.

              See [examples](https://docs.anthropic.com/en/api/messages-examples#vision) for
              more input examples.

              Note that if you want to include a
              [system prompt](https://docs.anthropic.com/en/docs/system-prompts), you can use
              the top-level `system` parameter — there is no `"system"` role for input
              messages in the Messages API.

          model: The model that will complete your prompt.\n\nSee
              [models](https://docs.anthropic.com/en/docs/models-overview) for additional
              details and options.

          stream: Whether to incrementally stream the response using server-sent events.

              See [streaming](https://docs.anthropic.com/en/api/messages-streaming) for
              details.

          metadata: An object describing metadata about the request.

          stop_sequences: Custom text sequences that will cause the model to stop generating.

              Our models will normally stop when they have naturally completed their turn,
              which will result in a response `stop_reason` of `"end_turn"`.

              If you want the model to stop generating when it encounters custom strings of
              text, you can use the `stop_sequences` parameter. If the model encounters one of
              the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
              and the response `stop_sequence` value will contain the matched stop sequence.

          system: System prompt.

              A system prompt is a way of providing context and instructions to Claude, such
              as specifying a particular goal or role. See our
              [guide to system prompts](https://docs.anthropic.com/en/docs/system-prompts).

          temperature: Amount of randomness injected into the response.

              Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
              for analytical / multiple choice, and closer to `1.0` for creative and
              generative tasks.

              Note that even with `temperature` of `0.0`, the results will not be fully
              deterministic.

          tool_choice: How the model should use the provided tools. The model can use a specific tool,
              any available tool, or decide by itself.

          tools: Definitions of tools that the model may use.

              If you include `tools` in your API request, the model may return `tool_use`
              content blocks that represent the model's use of those tools. You can then run
              those tools using the tool input generated by the model and then optionally
              return results back to the model using `tool_result` content blocks.

              Each tool definition includes:

              - `name`: Name of the tool.
              - `description`: Optional, but strongly-recommended description of the tool.
              - `input_schema`: [JSON schema](https://json-schema.org/) for the tool `input`
                shape that the model will produce in `tool_use` output content blocks.

              For example, if you defined `tools` as:

              ```json
              [
                {
                  "name": "get_stock_price",
                  "description": "Get the current stock price for a given ticker symbol.",
                  "input_schema": {
                    "type": "object",
                    "properties": {
                      "ticker": {
                        "type": "string",
                        "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
                      }
                    },
                    "required": ["ticker"]
                  }
                }
              ]
              ```

              And then asked the model "What's the S&P 500 at today?", the model might produce
              `tool_use` content blocks in the response like this:

              ```json
              [
                {
                  "type": "tool_use",
                  "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "name": "get_stock_price",
                  "input": { "ticker": "^GSPC" }
                }
              ]
              ```

              You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an
              input, and return the following back to the model in a subsequent `user`
              message:

              ```json
              [
                {
                  "type": "tool_result",
                  "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "content": "259.75 USD"
                }
              ]
              ```

              Tools can be used for workflows that include running client-side tools and
              functions, or more generally whenever you want the model to produce a particular
              JSON structure of output.

              See our [guide](https://docs.anthropic.com/en/docs/tool-use) for more details.

          top_k: Only sample from the top K options for each subsequent token.

              Used to remove "long tail" low probability responses.
              [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          top_p: Use nucleus sampling.

              In nucleus sampling, we compute the cumulative distribution over all the options
              for each subsequent token in decreasing probability order and cut it off once it
              reaches a particular probability specified by `top_p`. You should either alter
              `temperature` or `top_p`, but not both.

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          betas: Optional header to specify the beta version(s) you want to use.

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        ...

    @overload
    async def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        stream: bool,
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> PromptCachingBetaMessage | AsyncStream[RawPromptCachingBetaMessageStreamEvent]:
        """
        Send a structured list of input messages with text and/or image content, and the
        model will generate the next message in the conversation.

        The Messages API can be used for either single queries or stateless multi-turn
        conversations.

        Args:
          max_tokens: The maximum number of tokens to generate before stopping.

              Note that our models may stop _before_ reaching this maximum. This parameter
              only specifies the absolute maximum number of tokens to generate.

              Different models have different maximum values for this parameter. See
              [models](https://docs.anthropic.com/en/docs/models-overview) for details.

          messages: Input messages.

              Our models are trained to operate on alternating `user` and `assistant`
              conversational turns. When creating a new `Message`, you specify the prior
              conversational turns with the `messages` parameter, and the model then generates
              the next `Message` in the conversation. Consecutive `user` or `assistant` turns
              in your request will be combined into a single turn.

              Each input message must be an object with a `role` and `content`. You can
              specify a single `user`-role message, or you can include multiple `user` and
              `assistant` messages.

              If the final message uses the `assistant` role, the response content will
              continue immediately from the content in that message. This can be used to
              constrain part of the model's response.

              Example with a single `user` message:

              ```json
              [{ "role": "user", "content": "Hello, Claude" }]
              ```

              Example with multiple conversational turns:

              ```json
              [
                { "role": "user", "content": "Hello there." },
                { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
                { "role": "user", "content": "Can you explain LLMs in plain English?" }
              ]
              ```

              Example with a partially-filled response from Claude:

              ```json
              [
                {
                  "role": "user",
                  "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
                },
                { "role": "assistant", "content": "The best answer is (" }
              ]
              ```

              Each input message `content` may be either a single `string` or an array of
              content blocks, where each block has a specific `type`. Using a `string` for
              `content` is shorthand for an array of one content block of type `"text"`. The
              following input messages are equivalent:

              ```json
              { "role": "user", "content": "Hello, Claude" }
              ```

              ```json
              { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
              ```

              Starting with Claude 3 models, you can also send image content blocks:

              ```json
              {
                "role": "user",
                "content": [
                  {
                    "type": "image",
                    "source": {
                      "type": "base64",
                      "media_type": "image/jpeg",
                      "data": "/9j/4AAQSkZJRg..."
                    }
                  },
                  { "type": "text", "text": "What is in this image?" }
                ]
              }
              ```

              We currently support the `base64` source type for images, and the `image/jpeg`,
              `image/png`, `image/gif`, and `image/webp` media types.

              See [examples](https://docs.anthropic.com/en/api/messages-examples#vision) for
              more input examples.

              Note that if you want to include a
              [system prompt](https://docs.anthropic.com/en/docs/system-prompts), you can use
              the top-level `system` parameter — there is no `"system"` role for input
              messages in the Messages API.

          model: The model that will complete your prompt.\n\nSee
              [models](https://docs.anthropic.com/en/docs/models-overview) for additional
              details and options.

          stream: Whether to incrementally stream the response using server-sent events.

              See [streaming](https://docs.anthropic.com/en/api/messages-streaming) for
              details.

          metadata: An object describing metadata about the request.

          stop_sequences: Custom text sequences that will cause the model to stop generating.

              Our models will normally stop when they have naturally completed their turn,
              which will result in a response `stop_reason` of `"end_turn"`.

              If you want the model to stop generating when it encounters custom strings of
              text, you can use the `stop_sequences` parameter. If the model encounters one of
              the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
              and the response `stop_sequence` value will contain the matched stop sequence.

          system: System prompt.

              A system prompt is a way of providing context and instructions to Claude, such
              as specifying a particular goal or role. See our
              [guide to system prompts](https://docs.anthropic.com/en/docs/system-prompts).

          temperature: Amount of randomness injected into the response.

              Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
              for analytical / multiple choice, and closer to `1.0` for creative and
              generative tasks.

              Note that even with `temperature` of `0.0`, the results will not be fully
              deterministic.

          tool_choice: How the model should use the provided tools. The model can use a specific tool,
              any available tool, or decide by itself.

          tools: Definitions of tools that the model may use.

              If you include `tools` in your API request, the model may return `tool_use`
              content blocks that represent the model's use of those tools. You can then run
              those tools using the tool input generated by the model and then optionally
              return results back to the model using `tool_result` content blocks.

              Each tool definition includes:

              - `name`: Name of the tool.
              - `description`: Optional, but strongly-recommended description of the tool.
              - `input_schema`: [JSON schema](https://json-schema.org/) for the tool `input`
                shape that the model will produce in `tool_use` output content blocks.

              For example, if you defined `tools` as:

              ```json
              [
                {
                  "name": "get_stock_price",
                  "description": "Get the current stock price for a given ticker symbol.",
                  "input_schema": {
                    "type": "object",
                    "properties": {
                      "ticker": {
                        "type": "string",
                        "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
                      }
                    },
                    "required": ["ticker"]
                  }
                }
              ]
              ```

              And then asked the model "What's the S&P 500 at today?", the model might produce
              `tool_use` content blocks in the response like this:

              ```json
              [
                {
                  "type": "tool_use",
                  "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "name": "get_stock_price",
                  "input": { "ticker": "^GSPC" }
                }
              ]
              ```

              You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an
              input, and return the following back to the model in a subsequent `user`
              message:

              ```json
              [
                {
                  "type": "tool_result",
                  "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
                  "content": "259.75 USD"
                }
              ]
              ```

              Tools can be used for workflows that include running client-side tools and
              functions, or more generally whenever you want the model to produce a particular
              JSON structure of output.

              See our [guide](https://docs.anthropic.com/en/docs/tool-use) for more details.

          top_k: Only sample from the top K options for each subsequent token.

              Used to remove "long tail" low probability responses.
              [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          top_p: Use nucleus sampling.

              In nucleus sampling, we compute the cumulative distribution over all the options
              for each subsequent token in decreasing probability order and cut it off once it
              reaches a particular probability specified by `top_p`. You should either alter
              `temperature` or `top_p`, but not both.

              Recommended for advanced use cases only. You usually only need to use
              `temperature`.

          betas: Optional header to specify the beta version(s) you want to use.

          extra_headers: Send extra headers

          extra_query: Add additional query parameters to the request

          extra_body: Add additional JSON properties to the request

          timeout: Override the client-level default timeout for this request, in seconds
        """
        ...

    @required_args(["max_tokens", "messages", "model"], ["max_tokens", "messages", "model", "stream"])
    async def create(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        metadata: MetadataParam | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        stream: Literal[False] | Literal[True] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: ToolChoiceParam | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        betas: List[AnthropicBetaParam] | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> PromptCachingBetaMessage | AsyncStream[RawPromptCachingBetaMessageStreamEvent]:
        if not is_given(timeout) and self._client.timeout == DEFAULT_TIMEOUT:
            timeout = 600
        extra_headers = {
            **strip_not_given(
                {
                    "anthropic-beta": ",".join(chain((str(e) for e in betas), ["prompt-caching-2024-07-31"]))
                    if is_given(betas)
                    else NOT_GIVEN
                }
            ),
            **(extra_headers or {}),
        }
        extra_headers = {"anthropic-beta": "prompt-caching-2024-07-31", **(extra_headers or {})}
        return await self._post(
            "/v1/messages?beta=prompt_caching",
            body=await async_maybe_transform(
                {
                    "max_tokens": max_tokens,
                    "messages": messages,
                    "model": model,
                    "metadata": metadata,
                    "stop_sequences": stop_sequences,
                    "stream": stream,
                    "system": system,
                    "temperature": temperature,
                    "tool_choice": tool_choice,
                    "tools": tools,
                    "top_k": top_k,
                    "top_p": top_p,
                },
                message_create_params.MessageCreateParams,
            ),
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=PromptCachingBetaMessage,
            stream=stream or False,
            stream_cls=AsyncStream[RawPromptCachingBetaMessageStreamEvent],
        )

    def stream(
        self,
        *,
        max_tokens: int,
        messages: Iterable[PromptCachingBetaMessageParam],
        model: ModelParam,
        metadata: message_create_params.Metadata | NotGiven = NOT_GIVEN,
        stop_sequences: List[str] | NotGiven = NOT_GIVEN,
        system: Union[str, Iterable[PromptCachingBetaTextBlockParam]] | NotGiven = NOT_GIVEN,
        temperature: float | NotGiven = NOT_GIVEN,
        tool_choice: message_create_params.ToolChoice | NotGiven = NOT_GIVEN,
        tools: Iterable[PromptCachingBetaToolParam] | NotGiven = NOT_GIVEN,
        top_k: int | NotGiven = NOT_GIVEN,
        top_p: float | NotGiven = NOT_GIVEN,
        # 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_headers: Headers | None = None,
        extra_query: Query | None = None,
        extra_body: Body | None = None,
        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    ) -> AsyncPromptCachingBetaMessageStreamManager:
        """Create a Message stream"""
        if not is_given(timeout) and self._client.timeout == DEFAULT_TIMEOUT:
            timeout = 600

        extra_headers = {
            "anthropic-beta": "prompt-caching-2024-07-31",
            "X-Stainless-Stream-Helper": "beta.prompt_caching.messages",
            **(extra_headers or {}),
        }
        request = self._post(
            "/v1/messages?beta=prompt_caching",
            body=maybe_transform(
                {
                    "max_tokens": max_tokens,
                    "messages": messages,
                    "model": model,
                    "metadata": metadata,
                    "stop_sequences": stop_sequences,
                    "stream": True,
                    "system": system,
                    "temperature": temperature,
                    "tool_choice": tool_choice,
                    "tools": tools,
                    "top_k": top_k,
                    "top_p": top_p,
                },
                message_create_params.MessageCreateParams,
            ),
            options=make_request_options(
                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
            ),
            cast_to=PromptCachingBetaMessage,
            stream=True,
            stream_cls=AsyncStream[RawPromptCachingBetaMessageStreamEvent],
        )
        return AsyncPromptCachingBetaMessageStreamManager(request)


class MessagesWithRawResponse:
    def __init__(self, messages: Messages) -> None:
        self._messages = messages

        self.create = _legacy_response.to_raw_response_wrapper(
            messages.create,
        )


class AsyncMessagesWithRawResponse:
    def __init__(self, messages: AsyncMessages) -> None:
        self._messages = messages

        self.create = _legacy_response.async_to_raw_response_wrapper(
            messages.create,
        )


class MessagesWithStreamingResponse:
    def __init__(self, messages: Messages) -> None:
        self._messages = messages

        self.create = to_streamed_response_wrapper(
            messages.create,
        )


class AsyncMessagesWithStreamingResponse:
    def __init__(self, messages: AsyncMessages) -> None:
        self._messages = messages

        self.create = async_to_streamed_response_wrapper(
            messages.create,
        )