Skip to main content
POST
/
v1
/
responses
Create a response
curl --request POST \
  --url https://api.tokenfactory.nebius.com/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "model": "<string>",
  "background": false,
  "include": [],
  "instructions": "<string>",
  "max_output_tokens": 123,
  "max_tool_calls": 123,
  "metadata": {},
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "prompt": {
    "id": "<string>",
    "variables": {},
    "version": "<string>"
  },
  "reasoning": {},
  "service_tier": "auto",
  "store": true,
  "stream": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "auto",
  "tools": [
    {
      "name": "<string>",
      "type": "<string>",
      "parameters": {},
      "strict": true,
      "defer_loading": true,
      "description": "<string>"
    }
  ],
  "top_logprobs": 1,
  "top_p": 0.5,
  "truncation": "disabled",
  "user": "<string>",
  "prompt_cache_key": "<string>"
}
'
import requests

url = "https://api.tokenfactory.nebius.com/v1/responses"

payload = {
    "input": "<string>",
    "model": "<string>",
    "background": False,
    "include": [],
    "instructions": "<string>",
    "max_output_tokens": 123,
    "max_tool_calls": 123,
    "metadata": {},
    "parallel_tool_calls": True,
    "previous_response_id": "<string>",
    "prompt": {
        "id": "<string>",
        "variables": {},
        "version": "<string>"
    },
    "reasoning": {},
    "service_tier": "auto",
    "store": True,
    "stream": True,
    "temperature": 1,
    "text": { "format": { "type": "<string>" } },
    "tool_choice": "auto",
    "tools": [
        {
            "name": "<string>",
            "type": "<string>",
            "parameters": {},
            "strict": True,
            "defer_loading": True,
            "description": "<string>"
        }
    ],
    "top_logprobs": 1,
    "top_p": 0.5,
    "truncation": "disabled",
    "user": "<string>",
    "prompt_cache_key": "<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({
    input: '<string>',
    model: '<string>',
    background: false,
    include: [],
    instructions: '<string>',
    max_output_tokens: 123,
    max_tool_calls: 123,
    metadata: {},
    parallel_tool_calls: true,
    previous_response_id: '<string>',
    prompt: {id: '<string>', variables: {}, version: '<string>'},
    reasoning: {},
    service_tier: 'auto',
    store: true,
    stream: true,
    temperature: 1,
    text: {format: {type: '<string>'}},
    tool_choice: 'auto',
    tools: [
      {
        name: '<string>',
        type: '<string>',
        parameters: {},
        strict: true,
        defer_loading: true,
        description: '<string>'
      }
    ],
    top_logprobs: 1,
    top_p: 0.5,
    truncation: 'disabled',
    user: '<string>',
    prompt_cache_key: '<string>'
  })
};

fetch('https://api.tokenfactory.nebius.com/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.tokenfactory.nebius.com/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([
    'input' => '<string>',
    'model' => '<string>',
    'background' => false,
    'include' => [
        
    ],
    'instructions' => '<string>',
    'max_output_tokens' => 123,
    'max_tool_calls' => 123,
    'metadata' => [
        
    ],
    'parallel_tool_calls' => true,
    'previous_response_id' => '<string>',
    'prompt' => [
        'id' => '<string>',
        'variables' => [
                
        ],
        'version' => '<string>'
    ],
    'reasoning' => [
        
    ],
    'service_tier' => 'auto',
    'store' => true,
    'stream' => true,
    'temperature' => 1,
    'text' => [
        'format' => [
                'type' => '<string>'
        ]
    ],
    'tool_choice' => 'auto',
    'tools' => [
        [
                'name' => '<string>',
                'type' => '<string>',
                'parameters' => [
                                
                ],
                'strict' => true,
                'defer_loading' => true,
                'description' => '<string>'
        ]
    ],
    'top_logprobs' => 1,
    'top_p' => 0.5,
    'truncation' => 'disabled',
    'user' => '<string>',
    'prompt_cache_key' => '<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://api.tokenfactory.nebius.com/v1/responses"

	payload := strings.NewReader("{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"max_tool_calls\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"variables\": {},\n    \"version\": \"<string>\"\n  },\n  \"reasoning\": {},\n  \"service_tier\": \"auto\",\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"<string>\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"name\": \"<string>\",\n      \"type\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true,\n      \"defer_loading\": true,\n      \"description\": \"<string>\"\n    }\n  ],\n  \"top_logprobs\": 1,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\",\n  \"user\": \"<string>\",\n  \"prompt_cache_key\": \"<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://api.tokenfactory.nebius.com/v1/responses")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"max_tool_calls\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"variables\": {},\n    \"version\": \"<string>\"\n  },\n  \"reasoning\": {},\n  \"service_tier\": \"auto\",\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"<string>\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"name\": \"<string>\",\n      \"type\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true,\n      \"defer_loading\": true,\n      \"description\": \"<string>\"\n    }\n  ],\n  \"top_logprobs\": 1,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\",\n  \"user\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\"\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://api.tokenfactory.nebius.com/v1/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  \"input\": \"<string>\",\n  \"model\": \"<string>\",\n  \"background\": false,\n  \"include\": [],\n  \"instructions\": \"<string>\",\n  \"max_output_tokens\": 123,\n  \"max_tool_calls\": 123,\n  \"metadata\": {},\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": \"<string>\",\n  \"prompt\": {\n    \"id\": \"<string>\",\n    \"variables\": {},\n    \"version\": \"<string>\"\n  },\n  \"reasoning\": {},\n  \"service_tier\": \"auto\",\n  \"store\": true,\n  \"stream\": true,\n  \"temperature\": 1,\n  \"text\": {\n    \"format\": {\n      \"type\": \"<string>\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"name\": \"<string>\",\n      \"type\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true,\n      \"defer_loading\": true,\n      \"description\": \"<string>\"\n    }\n  ],\n  \"top_logprobs\": 1,\n  \"top_p\": 0.5,\n  \"truncation\": \"disabled\",\n  \"user\": \"<string>\",\n  \"prompt_cache_key\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body
{
  "id": "<string>",
  "created_at": 123,
  "model": "<string>",
  "output": [
    {
      "id": "<string>",
      "content": [
        {
          "annotations": [
            {
              "file_id": "<string>",
              "filename": "<string>",
              "index": 123,
              "type": "<string>"
            }
          ],
          "text": "<string>",
          "type": "<string>",
          "logprobs": [
            {
              "token": "<string>",
              "bytes": [
                123
              ],
              "logprob": 123,
              "top_logprobs": [
                {
                  "token": "<string>",
                  "bytes": [
                    123
                  ],
                  "logprob": 123
                }
              ]
            }
          ]
        }
      ],
      "role": "<string>",
      "type": "<string>"
    }
  ],
  "parallel_tool_calls": true,
  "temperature": 123,
  "tools": [
    {
      "name": "<string>",
      "type": "<string>",
      "parameters": {},
      "strict": true,
      "defer_loading": true,
      "description": "<string>"
    }
  ],
  "top_p": 123,
  "background": true,
  "max_output_tokens": 123,
  "error": {
    "message": "<string>"
  },
  "incomplete_details": {},
  "instructions": "<string>",
  "metadata": {},
  "object": "response",
  "max_tool_calls": 123,
  "previous_response_id": "<string>",
  "prompt": {
    "id": "<string>",
    "variables": {},
    "version": "<string>"
  },
  "reasoning": {},
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "top_logprobs": 123,
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123,
      "input_tokens_per_turn": [
        123
      ],
      "cached_tokens_per_turn": [
        123
      ]
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 0,
      "tool_output_tokens": 0,
      "output_tokens_per_turn": [
        123
      ],
      "tool_output_tokens_per_turn": [
        123
      ]
    },
    "total_tokens": 123
  },
  "user": "<string>"
}
{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

​
Authorization
string
header
required

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

Query Parameters

​
ai_project_id
string | null

current project ID

Body

application/json
​
input
required

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

​
model
string
required

The model used for the chat completion.

​
background
boolean | null

Whether to run the model response in the background.

Example:

false

​
include
enum<string>[] | null

Specify additional output data to include in the model response.

Available options:
code_interpreter_call.outputs,
computer_call_output.output.image_url,
file_search_call.results,
message.input_image.image_url,
message.output_text.logprobs,
reasoning.encrypted_content
​
instructions
string | null

A system (or developer) message inserted into the model's context.

​
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.

​
max_tool_calls
integer | null

The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.

​
metadata
Metadata · object | null

Set of 16 key-value pairs that can be attached to an object.

​
parallel_tool_calls
boolean | null

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

​
previous_response_id
string | null

The unique ID of the previous response to the model.

​
prompt
ResponsePrompt · object | null

Reference to a prompt template and its variables.

​
reasoning
Reasoning · object | null

Configuration options for reasoning models.

​
service_tier
enum<string>
default:auto

The service tier to use for the request.

Available options:
auto,
default,
over-limit,
flex,
no-limit
Examples:

"auto"

"flex"

​
store
boolean | null

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

​
stream
boolean | null

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

​
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
​
text
ResponseTextConfig · object | null

Configuration options for a text response from the model.

​
tool_choice
default:auto

How the model should select which tool (or tools) to use when generating a response.

Available options:
none,
auto,
required
​
tools
(FunctionTool · object | FileSearchTool · object | ComputerTool · object | ComputerUsePreviewTool · object | WebSearchTool · object | Mcp · object | CodeInterpreter · object | ImageGeneration · object | LocalShell · object | FunctionShellTool · object | CustomTool · object | NamespaceTool · object | ToolSearchTool · object | WebSearchPreviewTool · object | ApplyPatchTool · object)[]

An array of tools the model may call while generating a response.

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

Learn more about function calling.

​
top_logprobs
integer | null

A non-negative integer specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

Required range: x >= 0
​
top_p
number | null

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
​
truncation
enum<string>
default:disabled

The truncation strategy to use for the model response.

Available options:
auto,
disabled
​
user
string | null

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

​
prompt_cache_key
string | null

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field.

Response

Successful Response

​
id
string
required
​
created_at
integer
required
​
model
string
required
​
output
(ResponseOutputMessage · object | ResponseFileSearchToolCall · object | ResponseFunctionToolCall · object | ResponseFunctionToolCallOutputItem · object | ResponseFunctionWebSearch · object | ResponseComputerToolCall · object | ResponseComputerToolCallOutputItem · object | ResponseReasoningItem · object | ResponseToolSearchCall · object | ResponseToolSearchOutputItem · object | AdditionalTools · object | ResponseCompactionItem · object | ImageGenerationCall · object | ResponseCodeInterpreterToolCall · object | LocalShellCall · object | LocalShellCallOutput · object | ResponseFunctionShellToolCall · object | ResponseFunctionShellToolCallOutput · object | ResponseApplyPatchToolCall · object | ResponseApplyPatchToolCallOutput · object | McpCall · object | McpListTools · object | McpApprovalRequest · object | McpApprovalResponse · object | ResponseCustomToolCall · object | ResponseCustomToolCallOutputItem · object)[]
required

An output message from the model.

​
parallel_tool_calls
boolean
required
​
temperature
number
required
​
tool_choice
required
Available options:
none,
auto,
required
​
tools
(FunctionTool · object | FileSearchTool · object | ComputerTool · object | ComputerUsePreviewTool · object | WebSearchTool · object | Mcp · object | CodeInterpreter · object | ImageGeneration · object | LocalShell · object | FunctionShellTool · object | CustomTool · object | NamespaceTool · object | ToolSearchTool · object | WebSearchPreviewTool · object | ApplyPatchTool · object)[]
required

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

Learn more about function calling.

​
top_p
number
required
​
background
boolean
required
​
max_output_tokens
integer
required
​
service_tier
enum<string>
required

Represents the service tier for requests.

Attributes: Auto: Automatically choose the best available tier for the request (Default or OverLimit). Analyze response to determine which tier was used. Default: Return 429 errors on hitting the rate limit, do not exceed to the OverLimit tier. OverLimit: Indicate that the request was over the user limit. This tier cannot be set by user in the request, but us used in a response for tier=Auto. Flex: Do not consume rate-limit credits, but run with lower priority. May still result in 429 errors in case of if there is no resources to process.

Available options:
auto,
default,
over-limit,
flex,
no-limit
​
status
enum<string>
required
Available options:
completed,
failed,
in_progress,
cancelled,
queued,
incomplete
​
truncation
enum<string>
required
Available options:
auto,
disabled
​
error
ResponseError · object | null

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

​
incomplete_details
IncompleteDetails · object | null

Details about why the response is incomplete.

​
instructions
string | null
​
metadata
Metadata · object | null
​
object
string
default:response
Allowed value: "response"
​
max_tool_calls
integer | null
​
previous_response_id
string | null
​
prompt
ResponsePrompt · object | null

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

​
reasoning
Reasoning · object | null

gpt-5 and o-series models only

Configuration options for reasoning models.

​
text
ResponseTextConfig · object | null

Configuration options for a text response from the model.

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

​
top_logprobs
integer | null
​
usage
ResponseUsage · object | null
​
user
string | null