Skip to main content
POST
/
responses
Creates a model response 
curl --request POST \
  --url https://api.portkey.ai/v1/responses \
  --header 'Content-Type: application/json' \
  --header 'x-portkey-api-key: <api-key>' \
  --data '
{
  "model": "gpt-4o",
  "input": "<string>",
  "metadata": {},
  "temperature": 1,
  "top_p": 1,
  "user": "user-1234",
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "medium",
    "generate_summary": "concise"
  },
  "max_output_tokens": 123,
  "instructions": "<string>",
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tools": [
    {
      "type": "file_search",
      "vector_store_ids": [
        "<string>"
      ],
      "max_num_results": 123,
      "filters": {
        "type": "eq",
        "key": "<string>",
        "value": "<string>"
      },
      "ranking_options": {
        "ranker": "auto",
        "score_threshold": 0
      }
    }
  ],
  "tool_choice": "none",
  "truncation": "disabled",
  "include": [
    "file_search_call.results"
  ],
  "parallel_tool_calls": true,
  "store": true,
  "stream": false
}
'
{
  "metadata": {},
  "temperature": 1,
  "top_p": 1,
  "model": "gpt-4o",
  "instructions": "<string>",
  "tools": [
    {
      "type": "file_search",
      "vector_store_ids": [
        "<string>"
      ],
      "max_num_results": 123,
      "filters": {
        "type": "eq",
        "key": "<string>",
        "value": "<string>"
      },
      "ranking_options": {
        "ranker": "auto",
        "score_threshold": 0
      }
    }
  ],
  "tool_choice": "none",
  "id": "<string>",
  "object": "response",
  "created_at": 123,
  "error": {
    "code": "server_error",
    "message": "<string>"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "output": [
    {
      "id": "<string>",
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "<string>",
          "annotations": [
            {
              "type": "file_citation",
              "index": 123,
              "file_id": "<string>"
            }
          ]
        }
      ],
      "status": "in_progress"
    }
  ],
  "parallel_tool_calls": true,
  "user": "user-1234",
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "medium",
    "generate_summary": "concise"
  },
  "max_output_tokens": 123,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "truncation": "disabled",
  "status": "completed",
  "output_text": "<string>",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  }
}

Authorizations

​
x-portkey-api-key
string
header
required

Body

application/json
​
model
enum<string>
required

Model ID used to generate the response, like gpt-4o or o1. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

Available options:
o1-pro,
o1-pro-2025-03-19,
computer-use-preview,
computer-use-preview-2025-03-11
Example:

"gpt-4o"

​
input
required

Text, image, or file inputs to the model, used to generate a response.

Learn more:

​
metadata
object

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.

​
temperature
number | null
default:1

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.

Required range: 0 <= x <= 2
Example:

1

​
top_p
number | null
default:1

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.

Required range: 0 <= x <= 1
Example:

1

​
user
string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example:

"user-1234"

​
previous_response_id
string | null

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state.

​
reasoning
Reasoning · object

o-series models only

Configuration options for reasoning models.

​
max_output_tokens
integer | null

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

​
instructions
string | null

Inserts a system (or developer) message as the first item in the model's context.

When using along with previous_response_id, the instructions from a previous response will be not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

​
text
object

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

​
tools
(File search · object | Function · object | Computer use · object | Web search · object)[]

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.

The two categories of tools you can provide the model are:

  • Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  • Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code. Learn more about function calling.

A tool that searches for relevant content from uploaded files. Learn more about the file search tool.

​
tool_choice

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Available options:
none,
auto,
required
​
truncation
enum<string> | null
default:disabled

The truncation strategy to use for the model response.

  • auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
  • disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.
Available options:
auto,
disabled
​
include
enum<string>[] | null

Specify additional output data to include in the model response. Currently supported values are:

  • file_search_call.results: Include the search results of the file search tool call.
  • message.input_image.image_url: Include image urls from the input message.
  • computer_call_output.output.image_url: Include image urls from the computer call output.

Specify additional output data to include in the model response. Currently supported values are:

  • file_search_call.results: Include the search results of the file search tool call.
  • message.input_image.image_url: Include image urls from the input message.
  • computer_call_output.output.image_url: Include image urls from the computer call output.
Available options:
file_search_call.results,
message.input_image.image_url,
computer_call_output.output.image_url
​
parallel_tool_calls
boolean | null
default:true

Whether to allow the model to run tool calls in parallel.

​
store
boolean | null
default:true

Whether to store the generated model response for later retrieval via API.

​
stream
boolean | null
default: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.

Response

OK

​
metadata
object
required

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.

​
temperature
number | null
default:1
required

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.

Required range: 0 <= x <= 2
Example:

1

​
top_p
number | null
default:1
required

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.

Required range: 0 <= x <= 1
Example:

1

​
model
enum<string>
required

Model ID used to generate the response, like gpt-4o or o1. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

Available options:
o1-pro,
o1-pro-2025-03-19,
computer-use-preview,
computer-use-preview-2025-03-11
Example:

"gpt-4o"

​
instructions
string | null
required

Inserts a system (or developer) message as the first item in the model's context.

When using along with previous_response_id, the instructions from a previous response will be not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

​
tools
(File search · object | Function · object | Computer use · object | Web search · object)[]
required

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.

The two categories of tools you can provide the model are:

  • Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  • Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code. Learn more about function calling.

A tool that searches for relevant content from uploaded files. Learn more about the file search tool.

​
tool_choice
required

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Available options:
none,
auto,
required
​
id
string
required

Unique identifier for this Response.

​
object
enum<string>
required

The object type of this resource - always set to response.

Available options:
response
​
created_at
number
required

Unix timestamp (in seconds) of when this Response was created.

​
error
object
required

An error object returned when the model fails to generate a Response.

​
incomplete_details
object
required

Details about why the response is incomplete.

​
output
(Output message · object | File search tool call · object | Function tool call · object | Web search tool call · object | Computer tool call · object | Reasoning · object)[]
required

An array of content items generated by the model.

  • The length and order of items in the output array is dependent on the model's response.
  • Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.

An output message from the model.

​
parallel_tool_calls
boolean
default:true
required

Whether to allow the model to run tool calls in parallel.

​
user
string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example:

"user-1234"

​
previous_response_id
string | null

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state.

​
reasoning
Reasoning · object

o-series models only

Configuration options for reasoning models.

​
max_output_tokens
integer | null

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

​
text
object

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

​
truncation
enum<string> | null
default:disabled

The truncation strategy to use for the model response.

  • auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
  • disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.
Available options:
auto,
disabled
​
status
enum<string>

The status of the response generation. One of completed, failed, in_progress, or incomplete.

Available options:
completed,
failed,
in_progress,
incomplete
​
output_text
string | null

SDK-only convenience property that contains the aggregated text output from all output_text items in the output array, if any are present. Supported in the Python and JavaScript SDKs.

​
usage
object

Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.