MessageCountTokensParams Class — anthropic-sdk-python Architecture

Source Code

src/anthropic/types/beta/message_count_tokens_params.py lines 41–252

class MessageCountTokensParams(TypedDict, total=False):
    messages: Required[Iterable[BetaMessageParam]]
    """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" }] }
    ```

    See [input examples](https://docs.claude.com/en/api/messages-examples).

    Note that if you want to include a
    [system prompt](https://docs.claude.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.

    There is a limit of 100,000 messages in a single request.
    """

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

    context_management: Optional[BetaContextManagementConfigParam]
    """Context management configuration.

    This allows you to control how Claude manages context across multiple requests,
    such as whether to clear function results or not.