Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Openai Openai python Response Prompt

From Leeroopedia
Knowledge Sources
Domains API_Types, Responses_API
Last Updated 2026-02-15 00:00 GMT

Overview

Concrete type for representing a reference to a reusable prompt template and its variable substitutions, provided by the openai-python SDK.

Description

ResponsePrompt is a Pydantic model that holds a reference to a stored prompt template. It contains an id field identifying the template, an optional variables dictionary that maps variable names to substitution values (which can be strings, ResponseInputText, ResponseInputImage, or ResponseInputFile objects), and an optional version string to pin a specific template revision. This enables the Responses API's reusable prompts feature.

Usage

Import this type when you need to inspect or type-check prompt template references returned from the API. For constructing prompt parameters to send to the API, use ResponsePromptParam instead.

Code Reference

Source Location

Signature

class ResponsePrompt(BaseModel):
    """Reference to a prompt template and its variables."""

    id: str
    variables: Optional[Dict[str, Variables]] = None
    version: Optional[str] = None

Import

from openai.types.responses import ResponsePrompt

I/O Contract

Fields

Name Type Required Description
id str Yes The unique identifier of the prompt template to use.
variables Optional[Dict[str, Variables]] No Optional map of values to substitute for variables in the prompt. Values can be strings or input types (text, image, file).
version Optional[str] No Optional version of the prompt template.

Usage Examples

import openai

client = openai.OpenAI()

response = client.responses.create(
    model="gpt-4o",
    input={
        "prompt": {
            "id": "prompt_abc123",
            "variables": {"user_name": "Alice", "topic": "quantum computing"},
            "version": "v2",
        }
    },
)

# The response.prompt field (if present) would be a ResponsePrompt instance
print(response)

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment