Implementation:Cohere ai Cohere python AssistantMessageResponse Model

Knowledge Sources	Cohere Python SDK
Domains	SDK, Chat
Last Updated	2026-02-15 14:00 GMT

Overview

The AssistantMessageResponse class is a Pydantic model representing a response message from the assistant role with a role indicator and structured content items.

Description

The AssistantMessageResponse model represents the assistant's message as returned in a Cohere chat API response. It includes a fixed role field set to the literal value "assistant", a list of AssistantMessageResponseContentItem objects representing the content (which can be text or thinking items), optional ToolCallV2 entries for tool invocations, a tool_plan for chain-of-thought reasoning, and optional Citation objects. This model extends UncheckedBaseModel and is auto-generated from the Cohere API definition by Fern.

Usage

Use this model when processing chat API responses. It is the primary structure returned as the assistant's message in the response object, providing access to the generated text, any tool calls, and citations.

Code Reference

Source Location

• Repository: Cohere Python SDK
• File: src/cohere/types/assistant_message_response.py

Signature

class AssistantMessageResponse(UncheckedBaseModel):
    role: typing.Literal["assistant"] = "assistant"
    tool_calls: typing.Optional[typing.List[ToolCallV2]] = None
    tool_plan: typing.Optional[str] = pydantic.Field(default=None)
    content: typing.Optional[typing.List[AssistantMessageResponseContentItem]] = None
    citations: typing.Optional[typing.List[Citation]] = None

Import

from cohere.types import AssistantMessageResponse

I/O Contract

Field	Type	Required	Default	Description
role	Literal["assistant"]	No	"assistant"	The role identifier, always set to "assistant".
tool_calls	Optional[List[ToolCallV2]]	No	None	List of tool calls made by the assistant during this turn.
tool_plan	Optional[str]	No	None	A chain-of-thought style reflection and plan that the model generates when working with Tools.
content	Optional[List[AssistantMessageResponseContentItem]]	No	None	List of content items, each being either text or thinking content.
citations	Optional[List[Citation]]	No	None	List of citations linking generated text to source documents.

Usage Examples

import cohere

client = cohere.ClientV2(api_key="YOUR_API_KEY")

response = client.chat(
    model="command-r-plus",
    messages=[
        {"role": "user", "content": "Explain the theory of relativity."},
    ],
)

# Access the AssistantMessageResponse
message = response.message
print(message.role)  # "assistant"

# Iterate over content items (text or thinking)
if message.content:
    for item in message.content:
        if item.type == "text":
            print(f"Text: {item.text}")
        elif item.type == "thinking":
            print(f"Thinking: {item.thinking}")

# Check for tool calls
if message.tool_calls:
    for tool_call in message.tool_calls:
        print(f"Tool call: {tool_call}")

# Check for citations
if message.citations:
    for citation in message.citations:
        print(f"Citation: {citation}")

Related Pages

• Environment:Cohere_ai_Cohere_python_Python_SDK_Runtime