Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model’s response.
Parameters
background: Optional[bool]
Whether to run the model response in the background. Learn more.
instructions: Optional[str]
A system (or developer) message inserted into the model’s context.
When using along with previous_response_id, the instructions from a previous
response will not be carried over to the next response. This makes it simple
to swap out system (or developer) messages in new responses.
max_output_tokens: Optional[int]
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
minimum16
max_tool_calls: Optional[int]
The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.
metadata: Optional[Metadata]
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
previous_response_id: Optional[str]
The unique ID of the previous response to the model. Use this to
create multi-turn conversations. Learn more about
conversation state. Cannot be used in conjunction with conversation.
prompt_cache_key: Optional[str]
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
safety_identifier: Optional[str]
A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
maxLength64
stream: Optional[Literal[false]]
If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.
temperature: Optional[float]
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p but not both.
minimum0
maximum2
top_logprobs: Optional[int]
An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested.
minimum0
maximum20
top_p: Optional[float]
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature but not both.
minimum0
maximum1
Deprecateduser: Optional[str]
This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations.
A stable identifier for your end-users.
Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.
Create a model response
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
input=[
{
"role": "user",
"content": [
{ "type": "input_text", "text": "what is in this file?" },
{
"type": "input_file",
"file_url": "https://www.berkshirehathaway.com/letters/2024ltr.pdf",
"detail": "auto"
}
]
}
]
)
print(response)
{
"id": "resp_686eef60237881a2bd1180bb8b13de430e34c516d176ff86",
"object": "response",
"created_at": 1752100704,
"status": "completed",
"completed_at": 1752100705,
"background": false,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"max_tool_calls": null,
"model": "gpt-5.4",
"output": [
{
"id": "msg_686eef60d3e081a29283bdcbc4322fd90e34c516d176ff86",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "The file seems to contain excerpts from a letter to the shareholders of Berkshire Hathaway Inc., likely written by Warren Buffett. It covers several topics:\n\n1. **Communication Philosophy**: Buffett emphasizes the importance of transparency and candidness in reporting mistakes and successes to shareholders.\n\n2. **Mistakes and Learnings**: The letter acknowledges past mistakes in business assessments and management hires, highlighting the importance of correcting errors promptly.\n\n3. **CEO Succession**: Mention of Greg Abel stepping in as the new CEO and continuing the tradition of honest communication.\n\n4. **Pete Liegl Story**: A detailed account of acquiring Forest River and the relationship with its founder, highlighting trust and effective business decisions.\n\n5. **2024 Performance**: Overview of business performance, particularly in insurance and investment activities, with a focus on GEICO's improvement.\n\n6. **Tax Contributions**: Discussion of significant tax payments to the U.S. Treasury, credited to shareholders' reinvestments.\n\n7. **Investment Strategy**: A breakdown of Berkshire\u2019s investments in both controlled subsidiaries and marketable equities, along with a focus on long-term holding strategies.\n\n8. **American Capitalism**: Reflections on America\u2019s economic development and Berkshire\u2019s role within it.\n\n9. **Property-Casualty Insurance**: Insights into the P/C insurance business model and its challenges and benefits.\n\n10. **Japanese Investments**: Information about Berkshire\u2019s investments in Japanese companies and future plans.\n\n11. **Annual Meeting**: Details about the upcoming annual gathering in Omaha, including schedule changes and new book releases.\n\n12. **Personal Anecdotes**: Light-hearted stories about family and interactions, conveying Buffett's personable approach.\n\n13. **Financial Performance Data**: Tables comparing Berkshire\u2019s annual performance to the S&P 500, showing impressive long-term gains.\n\nOverall, the letter reinforces Berkshire Hathaway's commitment to transparency, investment in both its businesses and the wider economy, and emphasizes strong leadership and prudent financial management."
}
],
"role": "assistant"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"service_tier": "default",
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_logprobs": 0,
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 8438,
"input_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0
},
"output_tokens": 398,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 8836
},
"user": null,
"metadata": {}
}
Create a model response
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
tools=[{
"type": "file_search",
"vector_store_ids": ["vs_1234567890"],
"max_num_results": 20
}],
input="What are the attributes of an ancient brown dragon?",
)
print(response)
{
"id": "resp_67ccf4c55fc48190b71bd0463ad3306d09504fb6872380d7",
"object": "response",
"created_at": 1741485253,
"status": "completed",
"completed_at": 1741485254,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "file_search_call",
"id": "fs_67ccf4c63cd08190887ef6464ba5681609504fb6872380d7",
"status": "completed",
"queries": [
"attributes of an ancient brown dragon"
],
"results": null
},
{
"type": "message",
"id": "msg_67ccf4c93e5c81909d595b369351a9d309504fb6872380d7",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The attributes of an ancient brown dragon include...",
"annotations": [
{
"type": "file_citation",
"index": 320,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 576,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 815,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 815,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1030,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1030,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1156,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
},
{
"type": "file_citation",
"index": 1225,
"file_id": "file-4wDz5b167pAf72nx1h9eiN",
"filename": "dragons.pdf"
}
]
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "file_search",
"filters": null,
"max_num_results": 20,
"ranking_options": {
"ranker": "auto",
"score_threshold": 0.0
},
"vector_store_ids": [
"vs_1234567890"
]
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 18307,
"input_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0
},
"output_tokens": 348,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 18655
},
"user": null,
"metadata": {}
}
Create a model response
from openai import OpenAI
client = OpenAI()
tools = [
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location", "unit"],
}
}
]
response = client.responses.create(
model="gpt-5.4",
tools=tools,
input="What is the weather like in Boston today?",
tool_choice="auto"
)
print(response)
{
"id": "resp_67ca09c5efe0819096d0511c92b8c890096610f474011cc0",
"object": "response",
"created_at": 1741294021,
"status": "completed",
"completed_at": 1741294022,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "function_call",
"id": "fc_67ca09c6bedc8190a7abfec07b1a1332096610f474011cc0",
"call_id": "call_unLAR8MvFNptuiZK6K6HCy5k",
"name": "get_current_weather",
"arguments": "{\"location\":\"Boston, MA\",\"unit\":\"celsius\"}",
"status": "completed"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "function",
"description": "Get the current weather in a given location",
"name": "get_current_weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit"
]
}
},
"required": [
"location",
"unit"
]
},
"strict": true
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 291,
"output_tokens": 23,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 314
},
"user": null,
"metadata": {}
}
Create a model response
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
input=[
{
"role": "user",
"content": [
{ "type": "input_text", "text": "what is in this image?" },
{
"type": "input_image",
"image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
}
]
}
]
)
print(response)
{
"id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41",
"object": "response",
"created_at": 1741476777,
"status": "completed",
"completed_at": 1741476778,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "message",
"id": "msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 328,
"input_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0
},
"output_tokens": 52,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 380
},
"user": null,
"metadata": {}
}
Create a model response
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="o3-mini",
input="How much wood would a woodchuck chuck?",
reasoning={
"effort": "high"
}
)
print(response)
{
"id": "resp_67ccd7eca01881908ff0b5146584e408072912b2993db808",
"object": "response",
"created_at": 1741477868,
"status": "completed",
"completed_at": 1741477869,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "o1-2024-12-17",
"output": [
{
"type": "message",
"id": "msg_67ccd7f7b5848190a6f3e95d809f6b44072912b2993db808",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The classic tongue twister...",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": "high",
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 81,
"input_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0
},
"output_tokens": 1035,
"output_tokens_details": {
"reasoning_tokens": 832
},
"total_tokens": 1116
},
"user": null,
"metadata": {}
}
Create a model response
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
instructions="You are a helpful assistant.",
input="Hello!",
stream=True
)
for event in response:
print(event)
event: response.created
data: {"type":"response.created","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}}
event: response.in_progress
data: {"type":"response.in_progress","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}}
event: response.output_item.added
data: {"type":"response.output_item.added","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"in_progress","role":"assistant","content":[]}}
event: response.content_part.added
data: {"type":"response.content_part.added","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"","annotations":[]}}
event: response.output_text.delta
data: {"type":"response.output_text.delta","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"delta":"Hi"}
...
event: response.output_text.done
data: {"type":"response.output_text.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"text":"Hi there! How can I assist you today?"}
event: response.content_part.done
data: {"type":"response.content_part.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}}
event: response.output_item.done
data: {"type":"response.output_item.done","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}}
event: response.completed
data: {"type":"response.completed","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"completed","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-5.4","output":[{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":{"input_tokens":37,"output_tokens":11,"output_tokens_details":{"reasoning_tokens":0},"total_tokens":48},"user":null,"metadata":{}}}
Create a model response
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
input="Tell me a three sentence bedtime story about a unicorn."
)
print(response)
{
"id": "resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b",
"object": "response",
"created_at": 1741476542,
"status": "completed",
"completed_at": 1741476543,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "message",
"id": "msg_67ccd2bf17f0819081ff3bb2cf6508e60bb6a6b452d3795b",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "In a peaceful grove beneath a silver moon, a unicorn named Lumina discovered a hidden pool that reflected the stars. As she dipped her horn into the water, the pool began to shimmer, revealing a pathway to a magical realm of endless night skies. Filled with wonder, Lumina whispered a wish for all who dream to find their own hidden magic, and as she glanced back, her hoofprints sparkled like stardust.",
"annotations": []
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 36,
"input_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0
},
"output_tokens": 87,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 123
},
"user": null,
"metadata": {}
}
Create a model response
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
tools=[{ "type": "web_search_preview" }],
input="What was a positive news story from today?",
)
print(response)
{
"id": "resp_67ccf18ef5fc8190b16dbee19bc54e5f087bb177ab789d5c",
"object": "response",
"created_at": 1741484430,
"status": "completed",
"completed_at": 1741484431,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"model": "gpt-5.4",
"output": [
{
"type": "web_search_call",
"id": "ws_67ccf18f64008190a39b619f4c8455ef087bb177ab789d5c",
"status": "completed"
},
{
"type": "message",
"id": "msg_67ccf190ca3881909d433c50b1f6357e087bb177ab789d5c",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "As of today, March 9, 2025, one notable positive news story...",
"annotations": [
{
"type": "url_citation",
"start_index": 442,
"end_index": 557,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
},
{
"type": "url_citation",
"start_index": 962,
"end_index": 1077,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
},
{
"type": "url_citation",
"start_index": 1336,
"end_index": 1451,
"url": "https://.../?utm_source=chatgpt.com",
"title": "..."
}
]
}
]
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": null,
"summary": null
},
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "web_search_preview",
"domains": [],
"search_context_size": "medium",
"user_location": {
"type": "approximate",
"city": null,
"country": "US",
"region": null,
"timezone": null
}
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 328,
"input_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0
},
"output_tokens": 356,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 684
},
"user": null,
"metadata": {}
}
Returns Examples
{
"id": "id",
"created_at": 0,
"error": {
"code": "server_error",
"message": "message"
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"instructions": "string",
"metadata": {
"foo": "string"
},
"model": "gpt-5.1",
"object": "response",
"output": [
{
"id": "id",
"content": [
{
"annotations": [
{
"file_id": "file_id",
"filename": "filename",
"index": 0,
"type": "file_citation"
}
],
"text": "text",
"type": "output_text",
"logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
}
],
"role": "assistant",
"status": "in_progress",
"type": "message",
"phase": "commentary"
}
],
"parallel_tool_calls": true,
"temperature": 1,
"tool_choice": "none",
"tools": [
{
"name": "name",
"parameters": {
"foo": "bar"
},
"strict": true,
"type": "function",
"allowed_callers": [
"direct"
],
"defer_loading": true,
"description": "description",
"output_schema": {
"foo": "bar"
}
}
],
"top_p": 1,
"background": true,
"completed_at": 0,
"conversation": {
"id": "id"
},
"max_output_tokens": 0,
"max_tool_calls": 0,
"moderation": {
"input": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
},
"output": {
"categories": {
"foo": true
},
"category_applied_input_types": {
"foo": [
"text"
]
},
"category_scores": {
"foo": 0
},
"flagged": true,
"model": "model",
"type": "moderation_result"
}
},
"output_text": "output_text",
"previous_response_id": "previous_response_id",
"prompt": {
"id": "id",
"variables": {
"foo": "string"
},
"version": "version"
},
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_options": {
"mode": "implicit",
"ttl": "30m"
},
"prompt_cache_retention": "in_memory",
"reasoning": {
"context": "auto",
"effort": "none",
"generate_summary": "auto",
"mode": "standard",
"summary": "auto"
},
"safety_identifier": "safety-identifier-1234",
"service_tier": "auto",
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "low"
},
"top_logprobs": 0,
"truncation": "auto",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cache_write_tokens": 0,
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"user": "user-1234"
}