Back to Services
Endpoints

OpenAI SDK

Using OnlySq AI models via OpenAI SDK. The API is compatible for calls from OpenAI libraries. This allows you to easily connect projects to the OnlySq API, use any of the 40+ available models for free, use it in projects such as Exteragram, etc.

Supported Languages

TypeScript / JavaScriptPythonJava.NETGo

Installation

First you need to install the required dependencies and import SDK.

python
pip install openai

Initializing Client

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.onlysq.ru/ai/openai/",
    api_key="openai"  # or your valid key
)

Chat Completions

Here's a basic example of using Chat Completions.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.onlysq.ru/ai/openai",
    api_key="openai",
)

completion = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {
            "role": "user",
            "content": "Say 5 short facts about AI.",
        },
    ],
)

print(completion.choices[0].message.content)

Example Response

Here are five short facts about AI:

  1. AI Learns from Data – AI systems improve by analyzing large amounts of data, identifying patterns, and making predictions.
  2. Narrow vs. General AI – Most AI today is "narrow" (task-specific), while "general AI" (human-like reasoning) is still theoretical.
  3. AI Powers Everyday Tech – Virtual assistants (Siri, Alexa), recommendations (Netflix, Spotify), and spam filters all use AI.
  4. Ethical Concerns Exist – AI raises issues like bias in algorithms, job displacement, and privacy risks.
  5. AI is Evolving Fast – Breakthroughs in deep learning and generative AI (like ChatGPT) are rapidly advancing the field.

State Management

Use the messages parameter to build conversation history. Include system (developer) messages and multi-turn chat between user and assistant.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.onlysq.ru/ai/openai",
    api_key="openai",
)

completion = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {
            "role": "system",
            "content": "You are a neko-helper.",
        },
        {
            "role": "user",
            "content": "What's 5 + 5?",
        },
        {
            "role": "assistant",
            "content": "Nya~! 5 + 5 is 10, purr-fectly simple! 😸✨"
        },
        {
            "role": "user",
            "content": "Say what do you like",
        },
    ],
)

print(completion.choices[0].message.content)

Streaming Chat Completions

python
from openai import OpenAI

client = OpenAI(api_key="openai", base_url="https://api.onlysq.ru/ai/openai/")
messages = [
    {
        "role": "user",
        "content": "Write a one-line story about AI."
    }
]
r = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    stream=True
)

for chunk in r:
    print(chunk.choices[0].delta.content, end="")

Streaming Chunk Example

json
{
  "id": "chatcmpl_lQdhTfXn4yKoDlyCjuBpL0GfPZNonZufGqOyGl3wVpMhJRwP",
  "object": "chat.completion.chunk",
  "created": 1750612428,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": "te",
        "role": "assistant"
      },  
      "finish_reason": null
    }
  ],
  "usage": null
}

Supported Parameters

  • model - required
  • messages - required
Learn more in docs