Responses

Create a model response

curl --request POST \
  --url https://api.ttapi.io/v1/responses \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.4-mini",
  "input": "Explain quantum computing in simple terms.",
  "instructions": "<string>",
  "previous_response_id": "<string>",
  "conversation": "<string>",
  "background": false,
  "include": [],
  "max_output_tokens": 2,
  "max_tool_calls": 2,
  "metadata": {},
  "parallel_tool_calls": true,
  "prompt_cache_key": "<string>",
  "reasoning": {},
  "safety_identifier": "<string>",
  "store": true,
  "stream": false,
  "stream_options": {
    "include_obfuscation": true
  },
  "temperature": 1,
  "text": {
    "format": {}
  },
  "tools": [
    {}
  ],
  "top_logprobs": 10,
  "top_p": 0.5,
  "truncation": "disabled"
}
'

import requests

url = "https://api.ttapi.io/v1/responses"

payload = {
    "model": "gpt-5.4-mini",
    "input": "Explain quantum computing in simple terms.",
    "instructions": "<string>",
    "previous_response_id": "<string>",
    "conversation": "<string>",
    "background": False,
    "include": [],
    "max_output_tokens": 2,
    "max_tool_calls": 2,
    "metadata": {},
    "parallel_tool_calls": True,
    "prompt_cache_key": "<string>",
    "reasoning": {},
    "safety_identifier": "<string>",
    "store": True,
    "stream": False,
    "stream_options": { "include_obfuscation": True },
    "temperature": 1,
    "text": { "format": {} },
    "tools": [{}],
    "top_logprobs": 10,
    "top_p": 0.5,
    "truncation": "disabled"
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-5.4-mini',
    input: 'Explain quantum computing in simple terms.',
    instructions: '<string>',
    previous_response_id: '<string>',
    conversation: '<string>',
    background: false,
    include: [],
    max_output_tokens: 2,
    max_tool_calls: 2,
    metadata: {},
    parallel_tool_calls: true,
    prompt_cache_key: '<string>',
    reasoning: {},
    safety_identifier: '<string>',
    store: true,
    stream: false,
    stream_options: {include_obfuscation: true},
    temperature: 1,
    text: {format: {}},
    tools: [{}],
    top_logprobs: 10,
    top_p: 0.5,
    truncation: 'disabled'
  })
};

fetch('https://api.ttapi.io/v1/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.ttapi.io/v1/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' => 'gpt-5.4-mini',
    'input' => 'Explain quantum computing in simple terms.',
    'instructions' => '<string>',
    'previous_response_id' => '<string>',
    'conversation' => '<string>',
    'background' => false,
    'include' => [
        
    ],
    'max_output_tokens' => 2,
    'max_tool_calls' => 2,
    'metadata' => [
        
    ],
    'parallel_tool_calls' => true,
    'prompt_cache_key' => '<string>',
    'reasoning' => [
        
    ],
    'safety_identifier' => '<string>',
    'store' => true,
    'stream' => false,
    'stream_options' => [
        'include_obfuscation' => true
    ],
    'temperature' => 1,
    'text' => [
        'format' => [
                
        ]
    ],
    'tools' => [
        [
                
        ]
    ],
    'top_logprobs' => 10,
    'top_p' => 0.5,
    'truncation' => 'disabled'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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://api.ttapi.io/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"gpt-5.4-mini\",\n  \"input\": \"Explain quantum computing in simple terms.\",\n  \"instructions\": \"<string>\",\n  \"previous_response_id\": \"<string>\",\n  \"conversation\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"max_output_tokens\": 2,\n  \"max_tool_calls\": 2,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"prompt_cache_key\": \"<string>\",\n  \"reasoning\": {},\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\"\n}")

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

	req.Header.Add("Authorization", "<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.ttapi.io/v1/responses")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-5.4-mini\",\n  \"input\": \"Explain quantum computing in simple terms.\",\n  \"instructions\": \"<string>\",\n  \"previous_response_id\": \"<string>\",\n  \"conversation\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"max_output_tokens\": 2,\n  \"max_tool_calls\": 2,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"prompt_cache_key\": \"<string>\",\n  \"reasoning\": {},\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.ttapi.io/v1/responses")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-5.4-mini\",\n  \"input\": \"Explain quantum computing in simple terms.\",\n  \"instructions\": \"<string>\",\n  \"previous_response_id\": \"<string>\",\n  \"conversation\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"max_output_tokens\": 2,\n  \"max_tool_calls\": 2,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"prompt_cache_key\": \"<string>\",\n  \"reasoning\": {},\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\"\n}"

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

{
  "id": "resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b",
  "object": "<string>",
  "created_at": 1741476542,
  "model": "<string>",
  "output": [
    {
      "type": "<string>",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "text": "<string>",
          "refusal": "<string>",
          "annotations": [
            {}
          ],
          "logprobs": [
            {}
          ]
        }
      ],
      "call_id": "<string>",
      "name": "<string>",
      "arguments": "<string>"
    }
  ],
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "incomplete_details": {},
  "output_text": "<string>",
  "previous_response_id": "<string>",
  "store": true,
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "metadata": {}
}

{
  "status": "FAILED",
  "message": "\"prompt\" cannot be empty.",
  "data": {}
}

{
  "status": "FAILED",
  "message": "Wrong TT-API-KEY or email is not activated."
}

POST

responses

Create a model response

curl --request POST \
  --url https://api.ttapi.io/v1/responses \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.4-mini",
  "input": "Explain quantum computing in simple terms.",
  "instructions": "<string>",
  "previous_response_id": "<string>",
  "conversation": "<string>",
  "background": false,
  "include": [],
  "max_output_tokens": 2,
  "max_tool_calls": 2,
  "metadata": {},
  "parallel_tool_calls": true,
  "prompt_cache_key": "<string>",
  "reasoning": {},
  "safety_identifier": "<string>",
  "store": true,
  "stream": false,
  "stream_options": {
    "include_obfuscation": true
  },
  "temperature": 1,
  "text": {
    "format": {}
  },
  "tools": [
    {}
  ],
  "top_logprobs": 10,
  "top_p": 0.5,
  "truncation": "disabled"
}
'

import requests

url = "https://api.ttapi.io/v1/responses"

payload = {
    "model": "gpt-5.4-mini",
    "input": "Explain quantum computing in simple terms.",
    "instructions": "<string>",
    "previous_response_id": "<string>",
    "conversation": "<string>",
    "background": False,
    "include": [],
    "max_output_tokens": 2,
    "max_tool_calls": 2,
    "metadata": {},
    "parallel_tool_calls": True,
    "prompt_cache_key": "<string>",
    "reasoning": {},
    "safety_identifier": "<string>",
    "store": True,
    "stream": False,
    "stream_options": { "include_obfuscation": True },
    "temperature": 1,
    "text": { "format": {} },
    "tools": [{}],
    "top_logprobs": 10,
    "top_p": 0.5,
    "truncation": "disabled"
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-5.4-mini',
    input: 'Explain quantum computing in simple terms.',
    instructions: '<string>',
    previous_response_id: '<string>',
    conversation: '<string>',
    background: false,
    include: [],
    max_output_tokens: 2,
    max_tool_calls: 2,
    metadata: {},
    parallel_tool_calls: true,
    prompt_cache_key: '<string>',
    reasoning: {},
    safety_identifier: '<string>',
    store: true,
    stream: false,
    stream_options: {include_obfuscation: true},
    temperature: 1,
    text: {format: {}},
    tools: [{}],
    top_logprobs: 10,
    top_p: 0.5,
    truncation: 'disabled'
  })
};

fetch('https://api.ttapi.io/v1/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.ttapi.io/v1/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' => 'gpt-5.4-mini',
    'input' => 'Explain quantum computing in simple terms.',
    'instructions' => '<string>',
    'previous_response_id' => '<string>',
    'conversation' => '<string>',
    'background' => false,
    'include' => [
        
    ],
    'max_output_tokens' => 2,
    'max_tool_calls' => 2,
    'metadata' => [
        
    ],
    'parallel_tool_calls' => true,
    'prompt_cache_key' => '<string>',
    'reasoning' => [
        
    ],
    'safety_identifier' => '<string>',
    'store' => true,
    'stream' => false,
    'stream_options' => [
        'include_obfuscation' => true
    ],
    'temperature' => 1,
    'text' => [
        'format' => [
                
        ]
    ],
    'tools' => [
        [
                
        ]
    ],
    'top_logprobs' => 10,
    'top_p' => 0.5,
    'truncation' => 'disabled'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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://api.ttapi.io/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"gpt-5.4-mini\",\n  \"input\": \"Explain quantum computing in simple terms.\",\n  \"instructions\": \"<string>\",\n  \"previous_response_id\": \"<string>\",\n  \"conversation\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"max_output_tokens\": 2,\n  \"max_tool_calls\": 2,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"prompt_cache_key\": \"<string>\",\n  \"reasoning\": {},\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\"\n}")

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

	req.Header.Add("Authorization", "<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.ttapi.io/v1/responses")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-5.4-mini\",\n  \"input\": \"Explain quantum computing in simple terms.\",\n  \"instructions\": \"<string>\",\n  \"previous_response_id\": \"<string>\",\n  \"conversation\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"max_output_tokens\": 2,\n  \"max_tool_calls\": 2,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"prompt_cache_key\": \"<string>\",\n  \"reasoning\": {},\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.ttapi.io/v1/responses")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-5.4-mini\",\n  \"input\": \"Explain quantum computing in simple terms.\",\n  \"instructions\": \"<string>\",\n  \"previous_response_id\": \"<string>\",\n  \"conversation\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"max_output_tokens\": 2,\n  \"max_tool_calls\": 2,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"prompt_cache_key\": \"<string>\",\n  \"reasoning\": {},\n  \"safety_identifier\": \"<string>\",\n  \"store\": true,\n  \"stream\": false,\n  \"stream_options\": {\n    \"include_obfuscation\": true\n  },\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {}\n  },\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\"\n}"

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

{
  "id": "resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b",
  "object": "<string>",
  "created_at": 1741476542,
  "model": "<string>",
  "output": [
    {
      "type": "<string>",
      "id": "<string>",
      "status": "<string>",
      "role": "assistant",
      "content": [
        {
          "text": "<string>",
          "refusal": "<string>",
          "annotations": [
            {}
          ],
          "logprobs": [
            {}
          ]
        }
      ],
      "call_id": "<string>",
      "name": "<string>",
      "arguments": "<string>"
    }
  ],
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "incomplete_details": {},
  "output_text": "<string>",
  "previous_response_id": "<string>",
  "store": true,
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "metadata": {}
}

{
  "status": "FAILED",
  "message": "\"prompt\" cannot be empty.",
  "data": {}
}

{
  "status": "FAILED",
  "message": "Wrong TT-API-KEY or email is not activated."
}

The request and response fields follow the official Responses API format. See the OpenAI API reference for the complete specification.

Use this endpoint for text, image, and file inputs, structured outputs, tool calls, multi-turn conversations, background processing, and streaming responses.

Authorizations

Authorization

string

header

required

You can obtain your API key from the TTAPI Dashboard.

Body

application/json

Request body for the OpenAI-compatible Responses API.

model

string

Model ID used to generate the response. See Supported Models.

Example:

"gpt-5.4-mini"

input

Text, image, or file input to the model. A string is treated as a user message.

Example:

"Explain quantum computing in simple terms."

instructions

string

A system or developer message inserted into the model context. It is not carried over when previous_response_id is used.

previous_response_id

string

ID of the previous response for multi-turn interactions. Cannot be used together with conversation.

conversation

Conversation that this response belongs to.

background

boolean

default:false

Whether to run the response in the background.

include

enum<string>[]

Additional output data to include in the response.

Available options:

file_search_call.results,

web_search_call.results,

web_search_call.action.sources,

message.input_image.image_url,

computer_call_output.output.image_url,

code_interpreter_call.outputs,

reasoning.encrypted_content,

message.output_text.logprobs

max_output_tokens

integer

Maximum number of generated tokens, including visible output and reasoning tokens.

Required range: x >= 1

max_tool_calls

integer

Maximum total number of built-in tool calls processed for this response.

Required range: x >= 1

metadata

object

Up to 16 string key-value pairs attached to the response.

Show child attributes

parallel_tool_calls

boolean

default:true

Whether the model may call tools in parallel.

prompt

object

Reference to a reusable prompt template.

Show child attributes

prompt_cache_key

string

Stable key used to improve prompt cache hit rates.

prompt_cache_retention

enum<string>

Prompt cache retention policy.

Available options:

in-memory,

24h

reasoning

object

Reasoning configuration for supported models.

Show child attributes

safety_identifier

string

Stable identifier for the end user, used for abuse detection.

service_tier

enum<string>

Available options:

auto,

default,

flex,

scale,

priority

store

boolean

Whether to store the generated response for later retrieval.

stream

boolean

default:false

Whether to stream response events using server-sent events.

stream_options

object

Streaming options. Set only when stream is true.

Show child attributes

temperature

number

Sampling temperature. Change this or top_p, but generally not both.

Required range: 0 <= x <= 2

text

object

Show child attributes

tool_choice

Controls which tool or tools the model may call.

Available options:

none,

auto,

required

tools

object[]

Tools available to the model, including function and supported built-in tools.

top_logprobs

integer

Required range: 0 <= x <= 20

top_p

number

Required range: 0 <= x <= 1

truncation

enum<string>

default:disabled

Available options:

auto,

disabled

Response

Successful response. When stream is true, the endpoint returns server-sent events.

string

required

Example:

"resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b"

object

string

required

Allowed value: "response"

created_at

number

required

Example:

1741476542

status

enum<string>

required

Available options:

completed,

failed,

in_progress,

cancelled,

queued,

incomplete

model

string

required

output

object[]

required

Show child attributes

error

object | null

Show child attributes

incomplete_details

object | null

Show child attributes

output_text

string

read-only

SDK convenience property containing aggregated text output.

previous_response_id

string | null

store

boolean

usage

object

Show child attributes

metadata

object

Show child attributes

Last modified on July 15, 2026

Completions Messages

Image Generation

Video Generation

Music Generation

Text / LLM

Account

Authorizations

Body

Response