Chat Completions (OpenAI compatible)

Compatible with OpenAI POST /v1/chat/completions. The messages content in the request body is masked for PII before the model is called. SSE streaming is supported with stream: true.

POST/v1/chat/completions

Request body

requiredapplication/json

modelstringrequired

Target model identifier (defined in the panel).

messagesChatMessage[]required

min items 1

Show properties

Array of ChatMessage

rolestringrequired

Allowed:systemuserassistanttool

contentstringrequired

Message text. By default, personal data in the content of all roles (`system`, `user`, `assistant`, `tool`) is masked inside the gateway; only the masked form reaches the model.

streamboolean

If true, the response is returned as an SSE stream.

default: false

temperaturenumber

min 0 · max 2 · default: 1

max_tokensinteger

Maximum number of tokens to generate.

min 1

top_pnumber

min 0 · max 1

Responses

200Successful response

idstring

objectstring

createdinteger

modelstring

choicesChatChoice[]

Show properties

Array of ChatChoice

indexinteger

finish_reasonstring

messageChatMessage

Show properties

rolestringrequired

Allowed:systemuserassistanttool

contentstringrequired

Message text. By default, personal data in the content of all roles (`system`, `user`, `assistant`, `tool`) is masked inside the gateway; only the masked form reaches the model.

usageUsage

Show properties

prompt_tokensinteger

completion_tokensinteger

total_tokensinteger

401Missing or invalid virtual key

errorobject

Show properties

messagestring

typestring

429Quota or rate limit exceeded

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.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Ayşe Demir'in talebini özetle."},
    ],
)
print(resp.choices[0].message.content)

import requests

response = requests.post(
    "https://gw-tr.gurubase.io/v1/chat/completions",
    headers={
        "Content-Type": "application/json"
    },
    json={
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "system",
      "content": "string"
    }
  ],
  "stream": False,
  "temperature": 1,
  "max_tokens": 0,
  "top_p": 0
},
)

curl -X POST "https://gw-tr.gurubase.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "system",
      "content": "string"
    }
  ],
  "stream": false,
  "temperature": 1,
  "max_tokens": 0,
  "top_p": 0
}'

const response = await fetch("https://gw-tr.gurubase.io/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "system",
      "content": "string"
    }
  ],
  "stream": false,
  "temperature": 1,
  "max_tokens": 0,
  "top_p": 0
})
});

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1718000000,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "system",
        "content": "string"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}