Create response

curl --request POST \
  --url https://api.cogito.decart.ai/v1/responses \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": {},
  "instructions": "<string>",
  "stream": true,
  "max_output_tokens": 123,
  "tools": [
    {}
  ],
  "tool_choice": {},
  "parallel_tool_calls": true,
  "reasoning": {},
  "text": {},
  "store": true
}
'

import requests

url = "https://api.cogito.decart.ai/v1/responses"

payload = {
    "model": "<string>",
    "input": {},
    "instructions": "<string>",
    "stream": True,
    "max_output_tokens": 123,
    "tools": [{}],
    "tool_choice": {},
    "parallel_tool_calls": True,
    "reasoning": {},
    "text": {},
    "store": True
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

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

fetch('https://api.cogito.decart.ai/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.cogito.decart.ai/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' => '<string>',
    'input' => [
        
    ],
    'instructions' => '<string>',
    'stream' => true,
    'max_output_tokens' => 123,
    'tools' => [
        [
                
        ]
    ],
    'tool_choice' => [
        
    ],
    'parallel_tool_calls' => true,
    'reasoning' => [
        
    ],
    'text' => [
        
    ],
    'store' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "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.cogito.decart.ai/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"input\": {},\n  \"instructions\": \"<string>\",\n  \"stream\": true,\n  \"max_output_tokens\": 123,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": {},\n  \"parallel_tool_calls\": true,\n  \"reasoning\": {},\n  \"text\": {},\n  \"store\": true\n}")

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

	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.cogito.decart.ai/v1/responses")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"input\": {},\n  \"instructions\": \"<string>\",\n  \"stream\": true,\n  \"max_output_tokens\": 123,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": {},\n  \"parallel_tool_calls\": true,\n  \"reasoning\": {},\n  \"text\": {},\n  \"store\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cogito.decart.ai/v1/responses")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"input\": {},\n  \"instructions\": \"<string>\",\n  \"stream\": true,\n  \"max_output_tokens\": 123,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": {},\n  \"parallel_tool_calls\": true,\n  \"reasoning\": {},\n  \"text\": {},\n  \"store\": true\n}"

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

POST

responses

Create response

curl --request POST \
  --url https://api.cogito.decart.ai/v1/responses \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": {},
  "instructions": "<string>",
  "stream": true,
  "max_output_tokens": 123,
  "tools": [
    {}
  ],
  "tool_choice": {},
  "parallel_tool_calls": true,
  "reasoning": {},
  "text": {},
  "store": true
}
'

import requests

url = "https://api.cogito.decart.ai/v1/responses"

payload = {
    "model": "<string>",
    "input": {},
    "instructions": "<string>",
    "stream": True,
    "max_output_tokens": 123,
    "tools": [{}],
    "tool_choice": {},
    "parallel_tool_calls": True,
    "reasoning": {},
    "text": {},
    "store": True
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

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

fetch('https://api.cogito.decart.ai/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.cogito.decart.ai/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' => '<string>',
    'input' => [
        
    ],
    'instructions' => '<string>',
    'stream' => true,
    'max_output_tokens' => 123,
    'tools' => [
        [
                
        ]
    ],
    'tool_choice' => [
        
    ],
    'parallel_tool_calls' => true,
    'reasoning' => [
        
    ],
    'text' => [
        
    ],
    'store' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "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.cogito.decart.ai/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"input\": {},\n  \"instructions\": \"<string>\",\n  \"stream\": true,\n  \"max_output_tokens\": 123,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": {},\n  \"parallel_tool_calls\": true,\n  \"reasoning\": {},\n  \"text\": {},\n  \"store\": true\n}")

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

	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.cogito.decart.ai/v1/responses")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"input\": {},\n  \"instructions\": \"<string>\",\n  \"stream\": true,\n  \"max_output_tokens\": 123,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": {},\n  \"parallel_tool_calls\": true,\n  \"reasoning\": {},\n  \"text\": {},\n  \"store\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cogito.decart.ai/v1/responses")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"input\": {},\n  \"instructions\": \"<string>\",\n  \"stream\": true,\n  \"max_output_tokens\": 123,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": {},\n  \"parallel_tool_calls\": true,\n  \"reasoning\": {},\n  \"text\": {},\n  \"store\": true\n}"

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

OpenAI-compatible Responses endpoint for stateless text generation and function-tool workflows. Streaming and non-streaming requests use the same authentication, model access, usage accounting, and billing as chat completions.

This endpoint is stateless. It does not store response objects or support background responses, conversations, or previous_response_id. Send the complete request state in input on every call.

Request body

string

required

Model slug from the catalog.

string | array

required

A text prompt or an array of Responses input items. Message items, function_call, and function_call_output are supported. Vision-capable models also accept URL or inline-data input_image parts.

string

System or developer instructions for this response.

boolean

default:"false"

When true, returns typed Server-Sent Events such as response.output_text.delta and response.completed.

integer

Maximum output tokens. The gateway caps this at the model’s max_output_length.

array

Function tools the model may call. Hosted tools such as web search, file search, computer use, code interpreter, shell, and MCP are not supported.

string | object

default:"auto"

Function-tool selection using the OpenAI Responses shape.

boolean

Allow the model to return multiple function calls in one response.

object

Reasoning configuration. reasoning.effort is forwarded to compatible models.

object

Text output configuration. text.format accepts text, JSON object, and JSON schema formats on models that support structured outputs.

boolean

default:"false"

Must be false when provided. Cogito does not persist response objects.

Example

curl https://api.cogito.decart.ai/v1/responses \
  -H "Authorization: Bearer $COGITO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2.6",
    "input": "Write a one-line release note.",
    "max_output_tokens": 128,
    "store": false
  }'

Unsupported features

The gateway returns 400 unsupported_feature before inference for:

store: true, background: true, previous_response_id, conversation, hosted prompt, and max_tool_calls
automatic truncation (truncation: "auto")
hosted or custom non-function tools and their history items
file, audio, and video input; image file IDs; and output logprobs

Only POST /v1/responses is exposed. Retrieve, delete, input-items, and cancel routes are not available.

Streaming

Streaming responses preserve the Responses API’s typed SSE events. Usage is read from the terminal response event for billing. Provider-private nvext fields are removed before events leave the public gateway.

Chat

Models

Errors

Create response

Request body

Example

Unsupported features

Streaming

​Request body

​Example

​Unsupported features

​Streaming

Request body

Example

Unsupported features

Streaming