Responses API (OpenAI compatible)

Compatible with OpenAI POST /v1/responses. The input field can be a string or an array of messages. With masking enabled, detected PII fields in either form are replaced before the model call. If the masking step cannot run, the request stops fail-closed before the model call.

POST/v1/responses

Request body

requiredapplication/json

modelstringrequired

Target model identifier (defined in the panel).

inputstring | ChatMessage[]required

A string or an array of messages. With masking enabled, detected personal-data fields in either form are replaced inside the gateway before the model call.

Show properties

One of:

string

string

ChatMessage[]

Array of ChatMessage

rolestringrequired

Allowed:systemuserassistanttool

contentstringrequired

Message text. With masking enabled, detected personal-data fields in all roles (`system`, `user`, `assistant`, `tool`) are replaced with placeholders inside the gateway.

streamboolean

default: false

temperaturenumber

min 0 · max 2

max_output_tokensinteger

Maximum number of tokens to generate.

min 1

Responses

200Successful response

idstring

objectstring

created_atinteger

modelstring

statusstring

outputResponsesOutputItem[]

Show properties

Array of ResponsesOutputItem

idstring

typestring

statusstring

rolestring

contentResponsesContentPart[]

Show properties

Array of ResponsesContentPart

typestring

textstring

annotationsobject[]

usageUsage

Show properties

prompt_tokensinteger

completion_tokensinteger

total_tokensinteger

401Missing or invalid virtual key

errorobject

Show properties

messagestring

typestring

413The input exceeds the masking limit. The request is not forwarded to the model; split the text and retry.

errorobject

Show properties

messagestring

typestring

429Quota or rate limit exceeded

errorobject

Show properties

messagestring

typestring

502The masking step could not run. The request is **fail-closed** and is not forwarded to the model; there is no "send it unmasked" option.

errorobject

Show properties

messagestring

typestring

Request

from openai import OpenAI

client = OpenAI(
    base_url="https://gw-tr.gurubase.io/v1",
    api_key="SANAL_ANAHTAR",
)

resp = client.responses.create(
    model="gpt-4o-mini",
    input="Ahmet Yılmaz, TCKN 10000000382, adres değişikliği istiyor.",
)
print(resp.output_text)

import requests

response = requests.post(
    "https://gw-tr.gurubase.io/v1/responses",
    headers={
        "Content-Type": "application/json"
    },
    json={
  "model": "gpt-4o-mini",
  "input": "Ahmet Yılmaz, TCKN 10000000382, talebini iletti.",
  "stream": False,
  "temperature": 0,
  "max_output_tokens": 0
},
)

curl -X POST "https://gw-tr.gurubase.io/v1/responses" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-4o-mini",
  "input": "Ahmet Yılmaz, TCKN 10000000382, talebini iletti.",
  "stream": false,
  "temperature": 0,
  "max_output_tokens": 0
}'

const response = await fetch("https://gw-tr.gurubase.io/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
  "model": "gpt-4o-mini",
  "input": "Ahmet Yılmaz, TCKN 10000000382, talebini iletti.",
  "stream": false,
  "temperature": 0,
  "max_output_tokens": 0
})
});

Response

{
  "id": "resp_01ec5099f62feeda",
  "object": "response",
  "created_at": 1782136928,
  "model": "gpt-4o-mini",
  "status": "completed",
  "output": [
    {
      "id": "msg_01ec5099f62feeda",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Kayıt alındı.",
          "annotations": [
            {}
          ]
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}