OnlySq Documentation

Appearance

POST https://api.onlysq.ru/ai/v2

Generates a text response to a user message(s).

Request ​

This endpoint expects an object.

model string Required

The name of a OnlySq AI model which will process the request

request dict Required

Query data dictionary.

Contains:

  • messages list Required

    A list of chat messages in chronological order, representing a conversation between the user and the model. Messages can be from User, Assistant and System roles.

  • meta dict Optional

    An optional dictionary previously used by ImaGen models.

    Contains:

    • image_count int Optional

      Optional parameter, previously used when generating with ImaGen

Response ​

id string

Unique identifier for the generated reply. Useful for submitting feedback.

object string

Object initialization for OpenAI SDK.

created int

Timestamp in UNIX format.

model string

The model that processed the request.

answer string Disabled

The old version of receiving a response. Will be completely removed on 05/01/2025

choices list

The list of completion choices the model generated for the input prompt.

Contains:

  • index integer

    Index of generated response

  • message dict

    An object containing the response of the model that processed the request

    Contains:

    • role string

      A role of message, can be one of: User, Assistant, System.

    • content string

      A response text.

  • finish_reason string

    The reason a chat request has finished.

    • stop: The model finished sending a complete message.
    • error: The generation failed due to an internal error.

usage dict

Contains:

  • prompt_tokens int

    The number of billed input tokens.

  • completion_tokens int

    The number of billed output tokens.

  • total_tokens int

    Total number of billed tokens.

user int

Unique of user by API key. Useful for submitting feedback.

Examples ​

Request example ​

python
import requests

send = {
    "model": "gpt-4o-mini",
    "request": {
        "messages": [
            {
                "role": "user",
                "content": "Hi! Write a short one-line story"
            }
        ]
    }
}

request = requests.post('http://api.onlysq.ru/ai/v2', json=send)
print(response["choices"][0]["message"]["content"])

This returns the following response to the console:

Under the streetlight, she found the courage to let go of the letter—and the past.

Response example ​

json
{
    "id": "chat_XBt6z670WKm7L9BVoCcLZLzTNZ03UJhD6sWqAEUyTgaJvhJA",
    "object": "chat.completion",
    "created": 1745146202,
    "model": "gpt-4o-mini",
    "answer": "[OnlySq API] Warning: \"answer\" was disabled in the responses; we recommend rewriting your projects to ensure accessibility to OnlySq API2.0 AI models",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\"Under the full moon, the werewolf realized he'd forgotten his keys—again.\"",
                "refusal": null,
                "annotations": []
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 11,
        "completion_tokens": 19,
        "total_tokens": 30
    },
    "user": 0
}