Model Responses

curl --request POST \
  --url https://{gatewayBaseURL}/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": "<unknown>",
  "background": true,
  "include": [
    "<string>"
  ],
  "instructions": "<string>",
  "max_output_tokens": 123,
  "metadata": {},
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "<string>"
  },
  "store": true,
  "stream": true,
  "temperature": 123,
  "text": {
    "format": {}
  },
  "tool_choice": "none",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "user": "<string>"
}
'

import requests

url = "https://{gatewayBaseURL}/responses"

payload = {
    "model": "<string>",
    "input": "<unknown>",
    "background": True,
    "include": ["<string>"],
    "instructions": "<string>",
    "max_output_tokens": 123,
    "metadata": {},
    "parallel_tool_calls": True,
    "previous_response_id": "<string>",
    "reasoning": { "effort": "<string>" },
    "store": True,
    "stream": True,
    "temperature": 123,
    "text": { "format": {} },
    "tool_choice": "none",
    "tools": ["<unknown>"],
    "top_p": 123,
    "user": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    input: '<unknown>',
    background: true,
    include: ['<string>'],
    instructions: '<string>',
    max_output_tokens: 123,
    metadata: {},
    parallel_tool_calls: true,
    previous_response_id: '<string>',
    reasoning: {effort: '<string>'},
    store: true,
    stream: true,
    temperature: 123,
    text: {format: {}},
    tool_choice: 'none',
    tools: ['<unknown>'],
    top_p: 123,
    user: '<string>'
  })
};

fetch('https://{gatewayBaseURL}/responses', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://{gatewayBaseURL}/responses",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => '<string>',
    'input' => '<unknown>',
    'background' => true,
    'include' => [
        '<string>'
    ],
    'instructions' => '<string>',
    'max_output_tokens' => 123,
    'metadata' => [
        
    ],
    'parallel_tool_calls' => true,
    'previous_response_id' => '<string>',
    'reasoning' => [
        'effort' => '<string>'
    ],
    'store' => true,
    'stream' => true,
    'temperature' => 123,
    'text' => [
        'format' => [
                
        ]
    ],
    'tool_choice' => 'none',
    'tools' => [
        '<unknown>'
    ],
    'top_p' => 123,
    'user' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://{gatewayBaseURL}/responses"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"input\": \"<unknown>\",\n  \"background\": true,\n  \"include\": [\n    \"<string>\"\n  ],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"reasoning\": {\n    \"effort\": \"<string>\"\n  },\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 123,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tool_choice\": \"none\",\n  \"tools\": [\n    \"<unknown>\"\n  ],\n  \"top_p\": 123,\n  \"user\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://{gatewayBaseURL}/responses")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"input\": \"<unknown>\",\n  \"background\": true,\n  \"include\": [\n    \"<string>\"\n  ],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"reasoning\": {\n    \"effort\": \"<string>\"\n  },\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 123,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tool_choice\": \"none\",\n  \"tools\": [\n    \"<unknown>\"\n  ],\n  \"top_p\": 123,\n  \"user\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{gatewayBaseURL}/responses")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"input\": \"<unknown>\",\n  \"background\": true,\n  \"include\": [\n    \"<string>\"\n  ],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"reasoning\": {\n    \"effort\": \"<string>\"\n  },\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 123,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tool_choice\": \"none\",\n  \"tools\": [\n    \"<unknown>\"\n  ],\n  \"top_p\": 123,\n  \"user\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "object": "<string>",
  "created_at": 123,
  "status": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "id": "<string>",
      "type": "<string>",
      "status": "<string>",
      "content": [
        {
          "type": "<string>",
          "annotations": [
            "<unknown>"
          ],
          "text": "<string>"
        }
      ],
      "role": "<string>"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "<unknown>",
    "summary": "<unknown>"
  },
  "service_tier": "<string>",
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "<string>",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "metadata": {},
  "provider": "<string>",
  "error": "<unknown>",
  "incomplete_details": "<unknown>",
  "instructions": "<unknown>",
  "user": "<unknown>"
}

POST

responses

Model Responses

curl --request POST \
  --url https://{gatewayBaseURL}/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": "<unknown>",
  "background": true,
  "include": [
    "<string>"
  ],
  "instructions": "<string>",
  "max_output_tokens": 123,
  "metadata": {},
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "<string>"
  },
  "store": true,
  "stream": true,
  "temperature": 123,
  "text": {
    "format": {}
  },
  "tool_choice": "none",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "user": "<string>"
}
'

import requests

url = "https://{gatewayBaseURL}/responses"

payload = {
    "model": "<string>",
    "input": "<unknown>",
    "background": True,
    "include": ["<string>"],
    "instructions": "<string>",
    "max_output_tokens": 123,
    "metadata": {},
    "parallel_tool_calls": True,
    "previous_response_id": "<string>",
    "reasoning": { "effort": "<string>" },
    "store": True,
    "stream": True,
    "temperature": 123,
    "text": { "format": {} },
    "tool_choice": "none",
    "tools": ["<unknown>"],
    "top_p": 123,
    "user": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    input: '<unknown>',
    background: true,
    include: ['<string>'],
    instructions: '<string>',
    max_output_tokens: 123,
    metadata: {},
    parallel_tool_calls: true,
    previous_response_id: '<string>',
    reasoning: {effort: '<string>'},
    store: true,
    stream: true,
    temperature: 123,
    text: {format: {}},
    tool_choice: 'none',
    tools: ['<unknown>'],
    top_p: 123,
    user: '<string>'
  })
};

fetch('https://{gatewayBaseURL}/responses', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://{gatewayBaseURL}/responses",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => '<string>',
    'input' => '<unknown>',
    'background' => true,
    'include' => [
        '<string>'
    ],
    'instructions' => '<string>',
    'max_output_tokens' => 123,
    'metadata' => [
        
    ],
    'parallel_tool_calls' => true,
    'previous_response_id' => '<string>',
    'reasoning' => [
        'effort' => '<string>'
    ],
    'store' => true,
    'stream' => true,
    'temperature' => 123,
    'text' => [
        'format' => [
                
        ]
    ],
    'tool_choice' => 'none',
    'tools' => [
        '<unknown>'
    ],
    'top_p' => 123,
    'user' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://{gatewayBaseURL}/responses"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"input\": \"<unknown>\",\n  \"background\": true,\n  \"include\": [\n    \"<string>\"\n  ],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"reasoning\": {\n    \"effort\": \"<string>\"\n  },\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 123,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tool_choice\": \"none\",\n  \"tools\": [\n    \"<unknown>\"\n  ],\n  \"top_p\": 123,\n  \"user\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://{gatewayBaseURL}/responses")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"input\": \"<unknown>\",\n  \"background\": true,\n  \"include\": [\n    \"<string>\"\n  ],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"reasoning\": {\n    \"effort\": \"<string>\"\n  },\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 123,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tool_choice\": \"none\",\n  \"tools\": [\n    \"<unknown>\"\n  ],\n  \"top_p\": 123,\n  \"user\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{gatewayBaseURL}/responses")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"input\": \"<unknown>\",\n  \"background\": true,\n  \"include\": [\n    \"<string>\"\n  ],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"reasoning\": {\n    \"effort\": \"<string>\"\n  },\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 123,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tool_choice\": \"none\",\n  \"tools\": [\n    \"<unknown>\"\n  ],\n  \"top_p\": 123,\n  \"user\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "object": "<string>",
  "created_at": 123,
  "status": "<string>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "id": "<string>",
      "type": "<string>",
      "status": "<string>",
      "content": [
        {
          "type": "<string>",
          "annotations": [
            "<unknown>"
          ],
          "text": "<string>"
        }
      ],
      "role": "<string>"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "<unknown>",
    "summary": "<unknown>"
  },
  "service_tier": "<string>",
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<unknown>"
  ],
  "top_p": 123,
  "truncation": "<string>",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "metadata": {},
  "provider": "<string>",
  "error": "<unknown>",
  "incomplete_details": "<unknown>",
  "instructions": "<unknown>",
  "user": "<unknown>"
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

x-tfy-metadata

string

Optional metadata for the request

x-tfy-provider-name

string

Name of the provider

Body

application/json

Parameters for generating model responses.

model

string

required

Model identifier to generate the response

input

any

Text, image, or file inputs to the model

background

boolean | null

Whether to run the model response in the background

include

string[] | null

Additional output data to include

instructions

string | null

System message as first item in context

max_output_tokens

number | null

Upper bound for tokens generated

metadata

object | null

Key-value pairs for additional information

Show child attributes

parallel_tool_calls

boolean | null

Allow parallel tool calls

previous_response_id

string | null

ID of previous response for multi-turn

reasoning

object | null

Configuration for reasoning models

Show child attributes

service_tier

enum<string> | null

Latency tier for processing

Available options:

auto,

default,

flex,

priority

store

boolean | null

Whether to store the response

stream

boolean | null

Enable streaming response

temperature

number | null

Sampling temperature between 0 and 2

text

object | null

Text response configuration

Show child attributes

tool_choice

Tool selection behavior

Available options:

none

tools

any[] | null

Available tools for the model

top_p

number | null

Nucleus sampling parameter

truncation

enum<string> | null

Truncation strategy

Available options:

auto,

disabled

user

string | null

End-user identifier

Response

Model Response generated successfully.

string

required

Response ID.

object

string

required

Object type.

created_at

number

required

Creation timestamp.

status

string

required

Response status.

max_output_tokens

number | null

required

Maximum output tokens allowed.

model

string

required

Model used for the response.

output

object[]

required

Show child attributes

parallel_tool_calls

boolean

required

Indicates if parallel tool calls were used.

previous_response_id

string | null

required

ID of the previous response, if any.

reasoning

object | null

required

Reasoning details.

Show child attributes

service_tier

string

required

Service tier.

store

boolean

required

Indicates if the response is stored.

temperature

number

required

Temperature setting for the model.

text

object

required

Show child attributes

tool_choice

string

required

Tool choice used.

tools

any[]

required

Tools used in the response.

top_p

number

required

Top-p sampling parameter.

truncation

string

required

Truncation setting.

usage

object

required

Show child attributes

metadata

object | null

required

Additional metadata.

provider

string

required

Provider of the response.

error

any

Provider error object when the response failed.

incomplete_details

any

Reason the response was cut off, e.g. max_output_tokens or content_filter.

instructions

any

Instructions provided for the response.

user

any

End-user identifier echoed from the request.

Delete Model Response Model Responses Compact

⌘I

Get Started

LLM Gateway

MCP Registry and Gateway

Skills Registry

Prompt Registry

Guardrails and Security

Observability

Deployment

Admin Guide

Chat

Messages

Embeddings

Rerank

Responses

Image

Audio

Batch

Files

Fine-tuning

Moderations

Models

Model Responses

Authorizations

Headers

Body

Response