Run OpenAI Responses API (OpenAI only)

curl --request POST \
  --url https://api.egp.scale.com/v5/responses \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "<string>",
  "input": "<string>",
  "include": [
    "<string>"
  ],
  "instructions": "<string>",
  "max_output_tokens": 123,
  "metadata": {},
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {},
  "store": true,
  "stream": true,
  "temperature": 1,
  "text": {},
  "tool_choice": "<string>",
  "tools": [
    {}
  ],
  "top_p": 0.5
}
'

import requests

url = "https://api.egp.scale.com/v5/responses"

payload = {
    "model": "<string>",
    "input": "<string>",
    "include": ["<string>"],
    "instructions": "<string>",
    "max_output_tokens": 123,
    "metadata": {},
    "parallel_tool_calls": True,
    "previous_response_id": "<string>",
    "reasoning": {},
    "store": True,
    "stream": True,
    "temperature": 1,
    "text": {},
    "tool_choice": "<string>",
    "tools": [{}],
    "top_p": 0.5
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    input: '<string>',
    include: ['<string>'],
    instructions: '<string>',
    max_output_tokens: 123,
    metadata: {},
    parallel_tool_calls: true,
    previous_response_id: '<string>',
    reasoning: {},
    store: true,
    stream: true,
    temperature: 1,
    text: {},
    tool_choice: '<string>',
    tools: [{}],
    top_p: 0.5
  })
};

fetch('https://api.egp.scale.com/v5/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://api.egp.scale.com/v5/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' => '<string>',
    'include' => [
        '<string>'
    ],
    'instructions' => '<string>',
    'max_output_tokens' => 123,
    'metadata' => [
        
    ],
    'parallel_tool_calls' => true,
    'previous_response_id' => '<string>',
    'reasoning' => [
        
    ],
    'store' => true,
    'stream' => true,
    'temperature' => 1,
    'text' => [
        
    ],
    'tool_choice' => '<string>',
    'tools' => [
        [
                
        ]
    ],
    'top_p' => 0.5
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($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://api.egp.scale.com/v5/responses"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"input\": \"<string>\",\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  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {},\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_p\": 0.5\n}")

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

	req.Header.Add("x-api-key", "<api-key>")
	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://api.egp.scale.com/v5/responses")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"input\": \"<string>\",\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  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {},\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_p\": 0.5\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v5/responses")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"input\": \"<string>\",\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  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {},\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_p\": 0.5\n}"

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

{
  "id": "<string>",
  "created_at": 123,
  "model": "<string>",
  "output": [
    {
      "id": "<string>",
      "content": [
        {
          "annotations": [
            "<unknown>"
          ],
          "text": "<string>",
          "type": "output_text",
          "logprobs": "<unknown>"
        }
      ],
      "role": "assistant",
      "status": "in_progress",
      "type": "message",
      "phase": "commentary"
    }
  ],
  "parallel_tool_calls": true,
  "tool_choice": "none",
  "tools": [
    {
      "name": "<string>",
      "type": "function",
      "parameters": {},
      "strict": true,
      "description": "<string>"
    }
  ],
  "object": "response",
  "error": {
    "code": "server_error",
    "message": "<string>"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "instructions": "<string>",
  "metadata": {},
  "temperature": 123,
  "top_p": 123,
  "background": true,
  "completed_at": 123,
  "conversation": {
    "id": "<string>"
  },
  "max_output_tokens": 123,
  "max_tool_calls": 123,
  "previous_response_id": "<string>",
  "prompt": {
    "id": "<string>",
    "variables": {},
    "version": "<string>"
  },
  "prompt_cache_key": "<string>",
  "prompt_cache_retention": "in-memory",
  "reasoning": {
    "effort": "none",
    "generate_summary": "auto",
    "summary": "auto"
  },
  "safety_identifier": "<string>",
  "service_tier": "auto",
  "status": "completed",
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "low"
  },
  "top_logprobs": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Inference

Run OpenAI Responses API (OpenAI only)

Runs inference using the OpenAI Responses API contract, taking an input rather than a chat messages array.

This endpoint is restricted to OpenAI-vendor models: requests whose model (vendor/name) resolves to any other vendor are rejected with an unsupported-vendor error, unlike /v5/chat/completions and /v5/inference which support many vendors. Use it when you specifically need Responses API features such as previous_response_id chaining, instructions, or store; use /v5/chat/completions for the standard messages-based chat contract. When stream is set the response streams as server-sent events; otherwise a single response object is returned.

POST

responses

curl --request POST \
  --url https://api.egp.scale.com/v5/responses \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "<string>",
  "input": "<string>",
  "include": [
    "<string>"
  ],
  "instructions": "<string>",
  "max_output_tokens": 123,
  "metadata": {},
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {},
  "store": true,
  "stream": true,
  "temperature": 1,
  "text": {},
  "tool_choice": "<string>",
  "tools": [
    {}
  ],
  "top_p": 0.5
}
'

import requests

url = "https://api.egp.scale.com/v5/responses"

payload = {
    "model": "<string>",
    "input": "<string>",
    "include": ["<string>"],
    "instructions": "<string>",
    "max_output_tokens": 123,
    "metadata": {},
    "parallel_tool_calls": True,
    "previous_response_id": "<string>",
    "reasoning": {},
    "store": True,
    "stream": True,
    "temperature": 1,
    "text": {},
    "tool_choice": "<string>",
    "tools": [{}],
    "top_p": 0.5
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    input: '<string>',
    include: ['<string>'],
    instructions: '<string>',
    max_output_tokens: 123,
    metadata: {},
    parallel_tool_calls: true,
    previous_response_id: '<string>',
    reasoning: {},
    store: true,
    stream: true,
    temperature: 1,
    text: {},
    tool_choice: '<string>',
    tools: [{}],
    top_p: 0.5
  })
};

fetch('https://api.egp.scale.com/v5/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://api.egp.scale.com/v5/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' => '<string>',
    'include' => [
        '<string>'
    ],
    'instructions' => '<string>',
    'max_output_tokens' => 123,
    'metadata' => [
        
    ],
    'parallel_tool_calls' => true,
    'previous_response_id' => '<string>',
    'reasoning' => [
        
    ],
    'store' => true,
    'stream' => true,
    'temperature' => 1,
    'text' => [
        
    ],
    'tool_choice' => '<string>',
    'tools' => [
        [
                
        ]
    ],
    'top_p' => 0.5
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($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://api.egp.scale.com/v5/responses"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"input\": \"<string>\",\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  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {},\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_p\": 0.5\n}")

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

	req.Header.Add("x-api-key", "<api-key>")
	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://api.egp.scale.com/v5/responses")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"input\": \"<string>\",\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  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {},\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_p\": 0.5\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v5/responses")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"input\": \"<string>\",\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  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {},\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_p\": 0.5\n}"

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

{
  "id": "<string>",
  "created_at": 123,
  "model": "<string>",
  "output": [
    {
      "id": "<string>",
      "content": [
        {
          "annotations": [
            "<unknown>"
          ],
          "text": "<string>",
          "type": "output_text",
          "logprobs": "<unknown>"
        }
      ],
      "role": "assistant",
      "status": "in_progress",
      "type": "message",
      "phase": "commentary"
    }
  ],
  "parallel_tool_calls": true,
  "tool_choice": "none",
  "tools": [
    {
      "name": "<string>",
      "type": "function",
      "parameters": {},
      "strict": true,
      "description": "<string>"
    }
  ],
  "object": "response",
  "error": {
    "code": "server_error",
    "message": "<string>"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "instructions": "<string>",
  "metadata": {},
  "temperature": 123,
  "top_p": 123,
  "background": true,
  "completed_at": 123,
  "conversation": {
    "id": "<string>"
  },
  "max_output_tokens": 123,
  "max_tool_calls": 123,
  "previous_response_id": "<string>",
  "prompt": {
    "id": "<string>",
    "variables": {},
    "version": "<string>"
  },
  "prompt_cache_key": "<string>",
  "prompt_cache_retention": "in-memory",
  "reasoning": {
    "effort": "none",
    "generate_summary": "auto",
    "summary": "auto"
  },
  "safety_identifier": "<string>",
  "service_tier": "auto",
  "status": "completed",
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "low"
  },
  "top_logprobs": 123,
  "truncation": "auto",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

x-api-key

string

header

required

Headers

x-selected-account-id

string | null

Body

application/json

model

string

required

model specified as model_vendor/model, for example openai/gpt-4o

input

required

include

string[] | null

Which fields to include in the response

instructions

string | null

Instructions for the response generation

max_output_tokens

integer | null

Maximum number of output tokens

metadata

Metadata · object | null

Metadata for the response

parallel_tool_calls

boolean | null

Whether to enable parallel tool calls

previous_response_id

string | null

ID of the previous response for chaining

reasoning

Reasoning · object | null

Reasoning configuration for the response

store

boolean | null

Whether to store the response

stream

boolean | null

Whether to stream the response

temperature

number | null

Sampling temperature for randomness control

Required range: 0 <= x <= 2

text

Text · object | null

Text configuration parameters

tool_choice

Tool choice configuration

tools

Tools · object[] | null

Tools available for the response

top_p

number | null

Top-p sampling parameter

Required range: 0 <= x <= 1

truncation

enum<string> | null

Truncation configuration

Available options:

auto,

disabled

Response

Successful Response

Response Post-V5-/V5/Responses
ResponseAudioDeltaEvent
ResponseAudioDoneEvent
ResponseAudioTranscriptDeltaEvent
ResponseAudioTranscriptDoneEvent
ResponseCodeInterpreterCallCodeDeltaEvent
ResponseCodeInterpreterCallCodeDoneEvent
ResponseCodeInterpreterCallCompletedEvent
ResponseCodeInterpreterCallInProgressEvent
ResponseCodeInterpreterCallInterpretingEvent
ResponseCompletedEvent
ResponseContentPartAddedEvent
ResponseContentPartDoneEvent
ResponseCreatedEvent
ResponseErrorEvent
ResponseFileSearchCallCompletedEvent
ResponseFileSearchCallInProgressEvent
ResponseFileSearchCallSearchingEvent
ResponseFunctionCallArgumentsDeltaEvent
ResponseFunctionCallArgumentsDoneEvent
ResponseInProgressEvent
ResponseFailedEvent
ResponseIncompleteEvent
ResponseOutputItemAddedEvent
ResponseOutputItemDoneEvent
ResponseReasoningSummaryPartAddedEvent
ResponseReasoningSummaryPartDoneEvent
ResponseReasoningSummaryTextDeltaEvent
ResponseReasoningSummaryTextDoneEvent
ResponseReasoningTextDeltaEvent
ResponseReasoningTextDoneEvent
ResponseRefusalDeltaEvent
ResponseRefusalDoneEvent
ResponseTextDeltaEvent
ResponseTextDoneEvent
ResponseWebSearchCallCompletedEvent
ResponseWebSearchCallInProgressEvent
ResponseWebSearchCallSearchingEvent
ResponseImageGenCallCompletedEvent
ResponseImageGenCallGeneratingEvent
ResponseImageGenCallInProgressEvent
ResponseImageGenCallPartialImageEvent
ResponseMcpCallArgumentsDeltaEvent
ResponseMcpCallArgumentsDoneEvent
ResponseMcpCallCompletedEvent
ResponseMcpCallFailedEvent
ResponseMcpCallInProgressEvent
ResponseMcpListToolsCompletedEvent
ResponseMcpListToolsFailedEvent
ResponseMcpListToolsInProgressEvent
ResponseOutputTextAnnotationAddedEvent
ResponseQueuedEvent
ResponseCustomToolCallInputDeltaEvent
ResponseCustomToolCallInputDoneEvent
GenericResponseEvent

string

required

created_at

number

required

model

required

output

required

An output message from the model.

Show child attributes

parallel_tool_calls

boolean

required

tool_choice

required

Available options:

none,

auto,

required

tools

required

Defines a function in your own code the model can choose to call.

Learn more about function calling.

Show child attributes

object

string

default:response

Allowed value: "response"

error

ResponseError · object | null

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

Show child attributes

incomplete_details

IncompleteDetails · object | null

Details about why the response is incomplete.

Show child attributes

instructions

metadata

Metadata · object | null

Show child attributes

temperature

number | null

top_p

number | null

background

boolean | null

completed_at

number | null

conversation

Conversation · object | null

The conversation that this response belonged to.

Input items and output items from this response were automatically added to this conversation.

Show child attributes

max_output_tokens

integer | null

max_tool_calls

integer | null

previous_response_id

string | null

prompt

ResponsePrompt · object | null

Reference to a prompt template and its variables. Learn more.

Show child attributes

prompt_cache_key

string | null

prompt_cache_retention

enum<string> | null

Available options:

in-memory,

24h

reasoning

Reasoning · object | null

gpt-5 and o-series models only

Configuration options for reasoning models.

Show child attributes

safety_identifier

string | null

service_tier

enum<string> | null

Available options:

auto,

default,

flex,

scale,

priority

status

enum<string> | null

Available options:

completed,

failed,

in_progress,

cancelled,

queued,

incomplete

text

ResponseTextConfig · object | null

Configuration options for a text response from the model.

Can be plain text or structured JSON data. Learn more:

Show child attributes

top_logprobs

integer | null

truncation

enum<string> | null

Available options:

auto,

disabled

usage

ResponseUsage · object | null

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

Show child attributes

user

string | null

Inference

Questions

Rubrics

Vector Stores

Files

Models

Agent Configs

Datasets

Dataset Items

Evaluations

Evaluation Groups

Evaluation Charts

Evaluation Dashboards

Evaluation Items

Spans

Span Assessment

Annotation Tasks

Credentials

Agentex Cloud Build

Agentex Cloud Deploy

Agentex Agent

SGP Cloud Secrets

Run OpenAI Responses API (OpenAI only)

Authorizations

Headers

Body

Response