responses

Create response

Create a response with streaming support. This endpoint corresponds to OpenAI’s Responses API.

Request

POST /responses

Request Body

Field	Type	Required	Description
model	string	Yes	Model name
input	string	Yes	Input content, required parameter. Can be:- String: Single text input- Message array: Structured conversation historyImportant limitations:- Messages only support basic fields (role, content, name)- Does not support tool_calls, tool_call_id and other tool-related fields- content field is required and cannot be null- To use tools, define them in the top-level tools parameter; model will call them on first responseNote: Responses API has deprecated messages parameter, now uses input parameter uniformly
instructions	string	No	System-level instructions to guide model behavior and response style (similar to system message)
temperature	number	No	Controls output randomness, higher values mean more random
top_p	number	No	Nucleus sampling parameter, controls output diversity
max_output_tokens	integer	No	Maximum number of tokens to generate
stream	boolean	No	Whether to enable streaming
modalities	Array<string (text, audio)>	No	Response modality types
tools	Array<ResponseTool>	No	Available tools list (using flat format)
tool_choice	string (none, auto, required)	No	Tool selection strategy
parallel_tool_calls	boolean	No	Whether to enable parallel function calling during tool use. When false, ensures exactly zero or one tool is called.
text	object	No	Text output configuration
previous_response_id	string	No	The ID of a previous response to continue the conversation from. This allows you to chain responses together and maintain conversation state.When using previous_response_id, the model will automatically have access to all previously produced reasoning items and conversation history.
store	boolean	No	Whether to store the generated model response for later retrieval via API.Defaults to true. Set to false to disable storage (required for ZDR organizations).
background	boolean	No	Whether to run the model response in the background asynchronously. Useful for long-running tasks.
reasoning	object	No	Configuration for reasoning models (e.g., o1, o3, gpt-5). Controls how the model uses reasoning tokens to “think” through the problem.
truncation	string (auto, disabled)	No	The truncation strategy to use for the model response.- auto: If input exceeds context window, truncate by dropping items from beginning- disabled: Request fails with 400 error if input exceeds context window (default)
stop	string	No	Up to 4 sequences where the API will stop generating further tokens
metadata	object	No	Additional metadata for tracking and organization purposes

Request Examples

Simple text input

{
  "model": "gpt-5.6-luna",
  "input": "Tell me a joke about programming",
  "instructions": "You are a funny assistant",
  "max_output_tokens": 500,
  "temperature": 0.7
}

Using message array (recommended)

{
  "model": "gpt-5.6-luna",
  "input": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ],
  "instructions": "You are a helpful assistant",
  "max_output_tokens": 1000
}

Multi-turn conversation

{
  "model": "qwen-plus",
  "input": [
    {
      "role": "user",
      "content": "What is artificial intelligence?"
    },
    {
      "role": "assistant",
      "content": "Artificial intelligence (AI) is..."
    },
    {
      "role": "user",
      "content": "Can you give me some examples?"
    }
  ],
  "instructions": "You are a knowledgeable AI tutor",
  "max_output_tokens": 2000,
  "stream": true
}

Request with tool calls

{
  "model": "gpt-5.6-luna",
  "input": [
    {
      "role": "user",
      "content": "What's the weather like in San Francisco?"
    }
  ],
  "instructions": "You are a helpful assistant with access to tools",
  "max_output_tokens": 2000,
  "temperature": 0.7,
  "modalities": [
    "text"
  ],
  "tools": [
    {
      "type": "function",
      "name": "get_weather",
      "description": "Get the current weather in a location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string"
          }
        },
        "required": [
          "location"
        ]
      }
    }
  ]
}

Multiple tool calls scenario

{
  "model": "gpt-5.6-luna",
  "input": [
    {
      "role": "user",
      "content": "Book a flight from NYC to London on Dec 25th and check the weather there"
    }
  ],
  "instructions": "You are a travel assistant. Use tools to help users with travel planning.",
  "tools": [
    {
      "type": "function",
      "name": "search_flights",
      "description": "Search for available flights",
      "parameters": {
        "type": "object",
        "properties": {
          "origin": {
            "type": "string",
            "description": "Departure city"
          },
          "destination": {
            "type": "string",
            "description": "Arrival city"
          },
          "date": {
            "type": "string",
            "description": "Travel date in YYYY-MM-DD format"
          }
        },
        "required": [
          "origin",
          "destination",
          "date"
        ]
      }
    },
    {
      "type": "function",
      "name": "get_weather",
      "description": "Get weather forecast",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string"
          },
          "date": {
            "type": "string"
          }
        },
        "required": [
          "location"
        ]
      }
    }
  ],
  "tool_choice": "auto",
  "max_output_tokens": 3000
}

Streaming with tool calls

{
  "model": "gpt-5.6-luna",
  "input": [
    {
      "role": "user",
      "content": "Calculate 15% tip on a $85.50 bill and tell me the total"
    }
  ],
  "instructions": "You are a helpful calculator assistant",
  "stream": true,
  "tools": [
    {
      "type": "function",
      "name": "calculate",
      "description": "Perform mathematical calculations",
      "parameters": {
        "type": "object",
        "properties": {
          "expression": {
            "type": "string",
            "description": "Mathematical expression to evaluate"
          }
        },
        "required": [
          "expression"
        ]
      }
    }
  ],
  "max_output_tokens": 1000
}

Required tool usage

{
  "model": "gpt-5.6-luna",
  "input": "Search for recent news about artificial intelligence",
  "instructions": "You must use the search tool to find current information",
  "tools": [
    {
      "type": "function",
      "name": "web_search",
      "description": "Search the web for information",
      "parameters": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string"
          },
          "num_results": {
            "type": "integer"
          }
        },
        "required": [
          "query"
        ]
      }
    }
  ],
  "tool_choice": "required",
  "max_output_tokens": 2000
}

Request with metadata

{
  "model": "gpt-5.6-luna",
  "input": "Summarize the key points from our discussion",
  "instructions": "You are a meeting assistant",
  "max_output_tokens": 1500,
  "temperature": 0.5,
  "top_p": 0.9,
  "metadata": {
    "user_id": "user_12345",
    "session_id": "session_abc",
    "conversation_id": "conv_xyz"
  }
}

Basic streaming response

{
  "model": "gpt-5.6-luna",
  "input": "Write a short poem about the ocean",
  "instructions": "You are a creative poet",
  "stream": true,
  "max_output_tokens": 500,
  "temperature": 0.9
}

JSON mode output

{
  "model": "gpt-5.6-luna",
  "input": "Extract person information and return as JSON: John Smith is 35 years old and works as a software engineer in San Francisco",
  "instructions": "Extract structured data and output in JSON format",
  "text": {
    "format": {
      "type": "json_object"
    }
  },
  "max_output_tokens": 500
}

Structured JSON with schema

{
  "model": "gpt-5.6-luna",
  "input": "Generate a user profile for software developer Alice Chen in JSON format",
  "instructions": "Create a detailed user profile following the schema",
  "text": {
    "format": {
      "type": "json_schema",
      "name": "user_profile",
      "schema": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "age": {
            "type": "integer"
          },
          "occupation": {
            "type": "string"
          },
          "location": {
            "type": "string"
          },
          "skills": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        },
        "required": [
          "name",
          "age",
          "occupation",
          "location",
          "skills"
        ],
        "additionalProperties": false
      },
      "strict": true
    }
  },
  "max_output_tokens": 800
}

Complete tool call flow with result

{
  "model": "gpt-5.6-luna",
  "input": [
    {
      "role": "user",
      "content": "What's the weather in Tokyo?"
    },
    {
      "role": "assistant",
      "content": "I'll check the weather for you."
    },
    {
      "role": "user",
      "content": "The weather tool returned: temperature 22°C, condition sunny, humidity 60%"
    }
  ],
  "instructions": "You are a helpful assistant. Synthesize tool results naturally.",
  "max_output_tokens": 500
}

Chained conversation with previous_response_id

{
  "model": "gpt-5.6-luna",
  "input": "Can you elaborate more on the second point?",
  "instructions": "You are a helpful assistant",
  "previous_response_id": "resp_abc123xyz456",
  "max_output_tokens": 1000
}

Background asynchronous task

{
  "model": "gpt-5.6-luna",
  "input": "Analyze this large dataset and provide insights: [dataset details...]",
  "instructions": "You are a data analyst",
  "background": true,
  "max_output_tokens": 5000,
  "temperature": 0.3
}

Reasoning mode for complex problems

{
  "model": "gpt-5-codex",
  "input": "A farmer needs to transport a fox, a chicken, and a bag of grain across a river. The boat can only carry the farmer and one item. If left alone, the fox will eat the chicken, and the chicken will eat the grain. How can the farmer get everything across safely?",
  "instructions": "Think through this step by step",
  "reasoning": {
    "effort": "high"
  },
  "max_output_tokens": 3000
}

Successful response

Response Schema

Field	Type	Required	Description
id	string	Yes	Unique identifier for the response
object	string	Yes	-
created_at	integer	Yes	Unix timestamp when the response was created
status	string (in_progress, completed, incomplete, failed, cancelled)	Yes	The status of the response
background	boolean	No	Whether the response is running in the background
billing	object	No	Billing information
completed_at	object	No	Unix timestamp when the response was completed
error	object	No	Error information if the response failed
incomplete_details	object	No	Details about why the response is incomplete
instructions	string	No	System-level instructions that guided the model’s behavior
max_output_tokens	integer	No	Maximum number of tokens to generate
max_tool_calls	object	No	Maximum number of tool calls allowed
model	string	Yes	The model used for the response
output	Array<ResponseOutputItem>	No	Array of output items produced by the model
parallel_tool_calls	boolean	No	Whether parallel tool calls are enabled
previous_response_id	object	No	ID of the previous response in a chain
prompt_cache_key	object	No	Key for prompt caching
prompt_cache_retention	object	No	Prompt cache retention policy
reasoning	object	No	Reasoning configuration
safety_identifier	object	No	Safety identifier for the response
service_tier	string (auto, default)	No	Service tier used
store	boolean	No	Whether to store the response
temperature	number	No	Temperature parameter used
text	object	No	Text format configuration
tool_choice	string (none, auto, required)	No	Tool choice strategy used
tools	Array<ResponseTool>	No	Tools that were available
top_logprobs	integer	No	Number of top log probabilities
top_p	number	No	Top-p sampling parameter used
truncation	string (auto, disabled)	No	Truncation strategy used
user	object	No	User identifier
metadata	object	No	Additional metadata
usage	object	No	Usage statistics (null when response is still in progress)

Response Examples

Simple text response

{
  "id": "resp_0af56b0fcfec6be7006949f1d2bf7881a1ac983a51aa13d9e9",
  "object": "response",
  "created_at": 1766453714,
  "status": "completed",
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1766453715,
  "error": null,
  "incomplete_details": null,
  "instructions": "You are a funny assistant",
  "max_output_tokens": 500,
  "max_tool_calls": null,
  "model": "gpt-5.6-luna-2024-07-18",
  "output": [
    {
      "id": "msg_0af56b0fcfec6be7006949f1d3675881a1a35d943785fb4b8b",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "Why do programmers prefer dark mode?\n\nBecause light attracts bugs!"
        }
      ],
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": null,
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 1,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 22,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 13,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 35
  },
  "user": null,
  "metadata": {}
}

Response with tool calls

{
  "id": "resp_tool_abc123",
  "object": "response",
  "created_at": 1766453800,
  "status": "completed",
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1766453802,
  "error": null,
  "incomplete_details": null,
  "instructions": "You are a helpful assistant with access to tools",
  "max_output_tokens": 2000,
  "model": "gpt-5.6-luna-2024-07-18",
  "output": [
    {
      "id": "msg_tool_output_123",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "I'll check the weather for you."
        }
      ],
      "role": "assistant"
    },
    {
      "id": "call_weather_001",
      "type": "function_call",
      "status": "completed",
      "call_id": "call_abc123",
      "name": "get_weather",
      "arguments": "{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}"
    }
  ],
  "parallel_tool_calls": true,
  "tools": [
    {
      "type": "function",
      "name": "get_weather",
      "description": "Get current weather",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string"
          },
          "unit": {
            "type": "string"
          }
        }
      }
    }
  ],
  "tool_choice": "auto",
  "temperature": 0.7,
  "usage": {
    "input_tokens": 45,
    "output_tokens": 28,
    "total_tokens": 73
  },
  "metadata": {}
}

JSON formatted response

{
  "id": "resp_json_xyz789",
  "object": "response",
  "created_at": 1766453900,
  "status": "completed",
  "background": false,
  "completed_at": 1766453901,
  "instructions": "Extract structured data",
  "max_output_tokens": 500,
  "model": "gpt-5.6-luna-2024-07-18",
  "output": [
    {
      "id": "msg_json_output",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "{\"name\": \"John Smith\", \"age\": 35, \"occupation\": \"software engineer\", \"location\": \"San Francisco\"}"
        }
      ],
      "role": "assistant"
    }
  ],
  "text": {
    "format": {
      "type": "json_object"
    }
  },
  "usage": {
    "input_tokens": 32,
    "output_tokens": 24,
    "total_tokens": 56
  }
}

Incomplete response (token limit)

{
  "id": "resp_incomplete_456",
  "object": "response",
  "created_at": 1766454000,
  "status": "incomplete",
  "background": false,
  "completed_at": 1766454002,
  "error": null,
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "instructions": "Write a detailed essay",
  "max_output_tokens": 100,
  "model": "gpt-5.6-luna-2024-07-18",
  "output": [
    {
      "id": "msg_incomplete",
      "type": "message",
      "status": "incomplete",
      "content": [
        {
          "type": "output_text",
          "text": "Artificial intelligence is a rapidly evolving field that encompasses machine learning, neural networks, and..."
        }
      ],
      "role": "assistant"
    }
  ],
  "usage": {
    "input_tokens": 15,
    "output_tokens": 100,
    "total_tokens": 115
  }
}

Failed response (error state)

{
  "id": "resp_failed_789",
  "object": "response",
  "created_at": 1766454100,
  "status": "failed",
  "background": false,
  "completed_at": null,
  "error": {
    "type": "server_error",
    "message": "Model service temporarily unavailable"
  },
  "instructions": "Answer the question",
  "max_output_tokens": 1000,
  "model": "gpt-5.6-luna-2024-07-18",
  "output": [],
  "usage": {
    "input_tokens": 10,
    "output_tokens": 0,
    "total_tokens": 10
  }
}

Background task response

{
  "id": "resp_background_999",
  "object": "response",
  "created_at": 1766454200,
  "status": "in_progress",
  "background": true,
  "completed_at": null,
  "instructions": "Analyze large dataset",
  "max_output_tokens": 5000,
  "model": "gpt-5.6-luna-2024-07-18",
  "output": [],
  "usage": null
}

Code Examples

JavaScript (Fetch)

const response = await fetch('https://api.uuroute.ai/v1/responses', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
  "model": "gpt-5.6-luna",
  "input": "Tell me a joke about programming",
  "instructions": "You are a funny assistant",
  "max_output_tokens": 500,
  "temperature": 0.7
})
});

const data = await response.json();
console.log(data);

Python (requests)

import requests

url = "https://api.uuroute.ai/v1/responses"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json={
  "model": "gpt-5.6-luna",
  "input": "Tell me a joke about programming",
  "instructions": "You are a funny assistant",
  "max_output_tokens": 500,
  "temperature": 0.7
}, headers=headers)
data = response.json()
print(data)

cURL

curl -X POST "https://api.uuroute.ai/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.6-luna","input":"Tell me a joke about programming","instructions":"You are a funny assistant","max_output_tokens":500,"temperature":0.7}'

Schema Reference

ResponseRequest

Field	Type	Required	Description
model	string	Yes	Model name
input	string	Yes	Input content, required parameter. Can be:- String: Single text input- Message array: Structured conversation historyImportant limitations:- Messages only support basic fields (role, content, name)- Does not support tool_calls, tool_call_id and other tool-related fields- content field is required and cannot be null- To use tools, define them in the top-level tools parameter; model will call them on first responseNote: Responses API has deprecated messages parameter, now uses input parameter uniformly
instructions	string	No	System-level instructions to guide model behavior and response style (similar to system message)
temperature	number	No	Controls output randomness, higher values mean more random
top_p	number	No	Nucleus sampling parameter, controls output diversity
max_output_tokens	integer	No	Maximum number of tokens to generate
stream	boolean	No	Whether to enable streaming
modalities	Array<string (text, audio)>	No	Response modality types
tools	Array<ResponseTool>	No	Available tools list (using flat format)
tool_choice	string (none, auto, required)	No	Tool selection strategy
parallel_tool_calls	boolean	No	Whether to enable parallel function calling during tool use. When false, ensures exactly zero or one tool is called.
text	object	No	Text output configuration
previous_response_id	string	No	The ID of a previous response to continue the conversation from. This allows you to chain responses together and maintain conversation state.When using previous_response_id, the model will automatically have access to all previously produced reasoning items and conversation history.
store	boolean	No	Whether to store the generated model response for later retrieval via API.Defaults to true. Set to false to disable storage (required for ZDR organizations).
background	boolean	No	Whether to run the model response in the background asynchronously. Useful for long-running tasks.
reasoning	object	No	Configuration for reasoning models (e.g., o1, o3, gpt-5). Controls how the model uses reasoning tokens to “think” through the problem.
truncation	string (auto, disabled)	No	The truncation strategy to use for the model response.- auto: If input exceeds context window, truncate by dropping items from beginning- disabled: Request fails with 400 error if input exceeds context window (default)
stop	string	No	Up to 4 sequences where the API will stop generating further tokens
metadata	object	No	Additional metadata for tracking and organization purposes

Message

Field	Type	Required	Description
role	string (system, user, assistant, tool)	Yes	Message role
content	object	No	Message content. Can be null when assistant message contains tool_calls.- user/system messages: Required, contains text or multimodal content- assistant messages: Optional when tool_calls is present; can be null or omitted- tool messages: Required, contains tool return results (usually JSON string)Important: In /v1/responses API, content field must exist and cannot be null.For /v1/chat/completions, content can be null when tool_calls is present.
name	string	No	Sender name
reasoning_content	string	No	Reasoning content
tool_calls	Array<ToolCall>	No	Tool calls list
tool_call_id	string	No	Tool call ID

MessageContent

Field	Type	Required	Description
type	string (text, image_url)	Yes	-
text	string	No	-
image_url	object	No	-

ImageURL

Field	Type	Required	Description
url	string	Yes	-
detail	string (auto, low, high)	No	-

ToolCall

Field	Type	Required	Description
id	string	Yes	-
type	string	Yes	-
function	object	Yes	-

FunctionCall

Field	Type	Required	Description
name	string	Yes	-
arguments	string	No	-

ResponseTool

Field	Type	Required	Description
type	string (function)	Yes	Tool type, currently only supports function
name	string	Yes	Function name
description	string	No	Function description, helps model understand when to call this function
parameters	object	No	Function parameter definition in JSON Schema format

ToolChoice

Field	Type	Required	Description
type	string	Yes	Tool type
function	object	Yes	-

ResponseObject

Field	Type	Required	Description
id	string	Yes	Unique identifier for the response
object	string	Yes	-
created_at	integer	Yes	Unix timestamp when the response was created
status	string (in_progress, completed, incomplete, failed, cancelled)	Yes	The status of the response
background	boolean	No	Whether the response is running in the background
billing	object	No	Billing information
completed_at	object	No	Unix timestamp when the response was completed
error	object	No	Error information if the response failed
incomplete_details	object	No	Details about why the response is incomplete
instructions	string	No	System-level instructions that guided the model’s behavior
max_output_tokens	integer	No	Maximum number of tokens to generate
max_tool_calls	object	No	Maximum number of tool calls allowed
model	string	Yes	The model used for the response
output	Array<ResponseOutputItem>	No	Array of output items produced by the model
parallel_tool_calls	boolean	No	Whether parallel tool calls are enabled
previous_response_id	object	No	ID of the previous response in a chain
prompt_cache_key	object	No	Key for prompt caching
prompt_cache_retention	object	No	Prompt cache retention policy
reasoning	object	No	Reasoning configuration
safety_identifier	object	No	Safety identifier for the response
service_tier	string (auto, default)	No	Service tier used
store	boolean	No	Whether to store the response
temperature	number	No	Temperature parameter used
text	object	No	Text format configuration
tool_choice	string (none, auto, required)	No	Tool choice strategy used
tools	Array<ResponseTool>	No	Tools that were available
top_logprobs	integer	No	Number of top log probabilities
top_p	number	No	Top-p sampling parameter used
truncation	string (auto, disabled)	No	Truncation strategy used
user	object	No	User identifier
metadata	object	No	Additional metadata
usage	object	No	Usage statistics (null when response is still in progress)

ResponseOutputItem

Field	Type	Required	Description
id	string	Yes	Unique identifier for output item
type	string (message, function_call, reasoning)	Yes	Output type (message for final response, function_call for tool calls, reasoning for reasoning trace)
status	string (completed, in_progress, incomplete)	No	Output status
role	string (user, assistant)	No	Message role
content	Array	No	Content array
call_id	string	No	Function call ID
name	string	No	Function name
arguments	string	No	Function arguments (JSON string)
output	string	No	Function output
summary	object	No	Natural-language summary of reasoning (for reasoning type), can be string or array
encrypted_content	object	No	Encrypted reasoning tokens for stateless workflows (for reasoning type)

ResponseUsage

Field	Type	Required	Description
input_tokens	integer	Yes	Number of tokens in the input
input_tokens_details	object	No	Details about input tokens
output_tokens	integer	Yes	Number of tokens in the output
output_tokens_details	object	No	Details about output tokens
total_tokens	integer	Yes	Total number of tokens (input + output)

API Overview - Learn about authentication and basic information
models - View models related APIs
chat - View chat related APIs
messages - View messages related APIs
completions - View completions related APIs
edits - View edits related APIs
images - View images related APIs
embeddings - View embeddings related APIs
engine-embeddings - View engine-embeddings related APIs
moderations - View moderations related APIs
audio - View audio related APIs
search - View search related APIs
proxy - View proxy related APIs

responses

Create response

Request

Request Body

Request Examples

Simple text input

Using message array (recommended)

Multi-turn conversation

Request with tool calls

Multiple tool calls scenario

Streaming with tool calls

Required tool usage

Request with metadata

Basic streaming response

JSON mode output

Structured JSON with schema

Complete tool call flow with result

Chained conversation with previous_response_id

Background asynchronous task

Reasoning mode for complex problems

Response Schema

Response Examples

Simple text response

Response with tool calls

JSON formatted response

Incomplete response (token limit)

Failed response (error state)

Background task response

Code Examples

JavaScript (Fetch)

Python (requests)

cURL

Schema Reference

ResponseRequest

Message

MessageContent

ImageURL

ToolCall

FunctionCall

ResponseTool

ToolChoice

ResponseObject

ResponseOutputItem

ResponseUsage

Related APIs