Implementation:Mistralai Client python ChatCompletionResponse

Knowledge Sources	Mistral Client Python Mistral AI Docs
Domains	NLP, API_Design
Last Updated	2026-02-15 14:00 GMT

Overview

Concrete tool for extracting generated text and metadata from chat completion API responses provided by the mistralai SDK.

Description

The ChatCompletionResponse Pydantic model encapsulates the complete API response. It contains a list of ChatCompletionChoice objects (each with a message and finish reason), usage statistics (UsageInfo with prompt, completion, and total token counts), and metadata (response ID, model name, creation timestamp). The primary way to access the generated text is through response.choices[0].message.content.

Usage

Access the response object returned by client.chat.complete() or client.chat.complete_async(). Always check choices[0].finish_reason to handle truncation (length), tool calls (tool_calls), or normal completion (stop).

Code Reference

Source Location

• Repository: client-python
• File: src/mistralai/client/models/chatcompletionresponse.py (L1-32), chatcompletionchoice.py (L1-33)

Signature

class ChatCompletionResponse(BaseModel):
    id: str
    object: str
    created: int
    model: str
    choices: List[ChatCompletionChoice]
    usage: UsageInfo

class ChatCompletionChoice(BaseModel):
    index: int
    message: AssistantMessage
    finish_reason: Optional[ChatCompletionChoiceFinishReason] = None

class UsageInfo(BaseModel):
    prompt_tokens: int
    completion_tokens: int
    total_tokens: int

Import

from mistralai.models import ChatCompletionResponse
# Typically received as return value from client.chat.complete()

I/O Contract

Inputs

Name	Type	Required	Description
response	ChatCompletionResponse	Yes	Return value from chat.complete() or chat.complete_async()

Outputs

Name	Type	Description
content	str	Generated text from choices[0].message.content
finish_reason	ChatCompletionChoiceFinishReason	"stop", "length", or "tool_calls"
usage	UsageInfo	Token consumption (prompt_tokens, completion_tokens, total_tokens)
tool_calls	Optional[List[ToolCall]]	Tool calls if the model invoked functions

Usage Examples

Extract Response Text

response = client.chat.complete(
    model="mistral-large-latest",
    messages=[UserMessage(content="Hello!")],
)

# Extract generated text
text = response.choices[0].message.content
print(text)

# Check finish reason
reason = response.choices[0].finish_reason
print(f"Finished because: {reason}")

# Access usage statistics
print(f"Tokens used: {response.usage.total_tokens}")
print(f"  Prompt: {response.usage.prompt_tokens}")
print(f"  Completion: {response.usage.completion_tokens}")

Related Pages

Implements Principle

• Principle:Mistralai_Client_python_Response_Processing