Implementation:Mistralai Client python GCP ChatCompletionStreamRequest

Knowledge Sources	Mistralai_Client_python
Domains	Chat_Completion, Streaming, Cloud_Integration
Last Updated	2026-02-15 14:00 GMT

Overview

Concrete tool for defining the request body of streaming chat completions in the GCP Mistral SDK.

Description

The ChatCompletionStreamRequest class is the streaming counterpart of ChatCompletionRequest for GCP-hosted Mistral models. It requires model as a mandatory string field (no default, unlike Azure's "azureai" default) and defaults stream to True. It shares the same message and parameter types as the non-streaming variant. Compared to the Azure version, the GCP streaming request does not include the safe_prompt parameter.

Usage

Import this model when constructing streaming chat completion requests for GCP-deployed Mistral models. The Chat.stream() method constructs this internally.

Code Reference

Source Location

Repository: Mistralai_Client_python
File: packages/mistralai_gcp/src/mistralai_gcp/models/chatcompletionstreamrequest.py
Lines: 1-213

Signature

class ChatCompletionStreamRequest(BaseModel):
    model: str
    messages: List[Messages]
    temperature: OptionalNullable[float] = UNSET
    top_p: Optional[float] = None
    max_tokens: OptionalNullable[int] = UNSET
    stream: Optional[bool] = True
    stop: Optional[Stop] = None
    random_seed: OptionalNullable[int] = UNSET
    metadata: OptionalNullable[Dict[str, Any]] = UNSET
    response_format: Optional[ResponseFormat] = None
    tools: OptionalNullable[List[Tool]] = UNSET
    tool_choice: Optional[ChatCompletionStreamRequestToolChoice] = None
    presence_penalty: Optional[float] = None
    frequency_penalty: Optional[float] = None
    n: OptionalNullable[int] = UNSET
    prediction: Optional[Prediction] = None
    parallel_tool_calls: Optional[bool] = None
    prompt_mode: OptionalNullable[MistralPromptMode] = UNSET

Import

from mistralai_gcp.models import ChatCompletionStreamRequest

I/O Contract

Inputs

Name	Type	Required	Description
model	str	Yes	Model ID (required, no default)
messages	List[Messages]	Yes	Conversation messages (System, User, Assistant, Tool)
temperature	OptionalNullable[float]	No	Sampling temperature
max_tokens	OptionalNullable[int]	No	Maximum tokens to generate
stream	Optional[bool]	No	Streaming flag (defaults to True)
tools	OptionalNullable[List[Tool]]	No	Available tools for function calling
tool_choice	Optional[Union[ToolChoice, ToolChoiceEnum]]	No	Tool selection strategy

Outputs

Name	Type	Description
Serialized dict	Dict[str, Any]	JSON-serializable streaming request body

Usage Examples

Building a GCP Streaming Request

from mistralai_gcp.models import (
    ChatCompletionStreamRequest,
    UserMessage,
)

request = ChatCompletionStreamRequest(
    model="mistral-large-latest",  # Required for GCP
    messages=[
        UserMessage(content="Explain quantum computing in simple terms."),
    ],
    temperature=0.5,
    max_tokens=500,
)

# stream defaults to True
assert request.stream is True

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment