message_count_tokens_params.py — anthropic-sdk-python Source File

Source Code

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

from __future__ import annotations

from typing import Union, Iterable
from typing_extensions import Required, TypedDict

from .model_param import ModelParam
from .message_param import MessageParam
from .text_block_param import TextBlockParam
from .tool_choice_param import ToolChoiceParam
from .output_config_param import OutputConfigParam
from .thinking_config_param import ThinkingConfigParam
from .message_count_tokens_tool_param import MessageCountTokensToolParam

__all__ = ["MessageCountTokensParams"]


class MessageCountTokensParams(TypedDict, total=False):
    messages: Required[Iterable[MessageParam]]
    """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"
      },
// ... (142 more lines)