Implementation:Cohere ai Cohere python V2Client Chat

Metadata
Source Repo	Cohere Python SDK
Source Doc	Cohere Chat API
Domains	NLP, Text_Generation, Chat_API
Last Updated	2026-02-15 14:00 GMT

Overview

Concrete method for sending non-streaming chat completion requests to Cohere language models.

Description

V2Client.chat sends a synchronous chat request to the Cohere V2 API. It delegates to RawV2Client.chat for HTTP transport and returns a parsed V2ChatResponse. Supports all generation parameters, tool definitions, document citations, response format constraints, safety modes, and thinking/reasoning modes.

Usage

Call after initializing a ClientV2 and constructing messages. Use for non-streaming completions. The method blocks until the full response is received.

Code Reference

Source Location: Repository cohere-ai/cohere-python, File src/cohere/v2/client.py, Lines L217-383
Signature:

def chat(
    self,
    *,
    model: str,
    messages: ChatMessages,
    tools: typing.Optional[typing.Sequence[ToolV2]] = OMIT,
    strict_tools: typing.Optional[bool] = OMIT,
    documents: typing.Optional[typing.Sequence[V2ChatRequestDocumentsItem]] = OMIT,
    citation_options: typing.Optional[CitationOptions] = OMIT,
    response_format: typing.Optional[ResponseFormatV2] = OMIT,
    safety_mode: typing.Optional[V2ChatRequestSafetyMode] = OMIT,
    max_tokens: typing.Optional[int] = OMIT,
    stop_sequences: typing.Optional[typing.Sequence[str]] = OMIT,
    temperature: typing.Optional[float] = OMIT,
    seed: typing.Optional[int] = OMIT,
    frequency_penalty: typing.Optional[float] = OMIT,
    presence_penalty: typing.Optional[float] = OMIT,
    k: typing.Optional[int] = OMIT,
    p: typing.Optional[float] = OMIT,
    logprobs: typing.Optional[bool] = OMIT,
    tool_choice: typing.Optional[V2ChatRequestToolChoice] = OMIT,
    thinking: typing.Optional[Thinking] = OMIT,
    priority: typing.Optional[int] = OMIT,
    request_options: typing.Optional[RequestOptions] = None,
) -> V2ChatResponse:

Import: from cohere import ClientV2 (access via client.chat())

I/O Contract

Name	Type	Required	Description
Inputs
`model`	`str`	Yes	Model name, e.g. `"command-a-03-2025"`
`messages`	`ChatMessages`	Yes	Conversation history
`tools`	`Optional[Sequence[ToolV2]]`	No	Tool/function definitions
`temperature`	`Optional[float]`	No	Sampling temperature (default 0.3)
`max_tokens`	`Optional[int]`	No	Max output tokens
`stop_sequences`	`Optional[Sequence[str]]`	No	Up to 5 stop strings
`seed`	`Optional[int]`	No	For deterministic sampling
`frequency_penalty`	`Optional[float]`	No	Repetition penalty (0-1)
`presence_penalty`	`Optional[float]`	No	Presence penalty (0-1)
`k`	`Optional[int]`	No	Top-k sampling (0-500)
`p`	`Optional[float]`	No	Nucleus sampling (0.01-0.99)
Outputs
Return value	`V2ChatResponse`	—	Response with `id`, `finish_reason`, `message` (containing content, tool_calls, citations), `usage`

Usage Examples

from cohere import ClientV2, UserChatMessageV2

client = ClientV2()
response = client.chat(
    model="command-a-03-2025",
    messages=[UserChatMessageV2(content="Explain quantum computing in simple terms.")],
    temperature=0.5,
    max_tokens=500,
)

print(response.message.content[0].text)
print(f"Tokens used: {response.usage}")

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment