FreeAI::Server::OpenAI — OpenAI API server based on built-in AI model scrapers.

Overview of the scraper

The scraper provides the ability to deploy your own OpenAI-compatible API server, which you can connect to from your applications (e.g., Cherry Studio, Cline, etc.) and scripts — both through the official OpenAI SDK and using standard HTTP requests. The scraper offers access to free and paid models that A-Parser scrapes.

List of supported models:

• FreeAI::ChatGPT
• FreeAI::Copilot
• FreeAI::DeepAI
• FreeAI::GoogleAI
• FreeAI::Kimi
• FreeAI::Perplexity

Go to DEMOBuy A-Parser Pro ($299)

Connecting to Cherry Studio

• Settings (upper right corner)
• List of providers, at the very bottom "add"
• Set an arbitrary name, Provider type must be OpenAI
• Enter API Key (any key)
• Enter the host (configured in FreeAI::Server::OpenAI), initially http://127.0.0.1:3000
• The "Manage" button adds the necessary models

View connection video

Connection via OpenAI SDK

Example code

import OpenAI from "openai";

(async function () {
    const openai = new OpenAI({
        baseURL: "http://127.0.0.1:3000/v1", //Link under which FreeAI::Server::OpenAI is hosted
        apiKey: "123", 
    });

    const completion = await openai.chat.completions.create({
        model: "FreeAI::ChatGPT", //Model - this is the name of the scraper from the FreeAI::Server::OpenAI list, the list of supported models is in the "Overview of the scraper" section
        messages: [{ role: "user", content: "Why is the sky blue?" }], //Request to the model
    });

    console.log(completion.choices[0].message.content); //Output of the response from the AI model
})();

Getting results via HTTP request

Example code

const resp = await fetch("http://127.0.0.1:3000/v1/chat/completions", {
    method: "POST",
    headers: {
        Authorization: "Bearer 123",
        "Content-Type": "application/json",
    },
    body: JSON.stringify({
        model: "FreeAI::ChatGPT", //Model - this is the name of the scraper from the FreeAI::Server::OpenAI list, the list of supported models is in the "Overview of the scraper" section
        messages: [{ role: "user", content: "Usage areas of nodejs" }], //Request to the model
    }),
});

if (!resp.ok) {
    const text = await resp.text();
    throw new Error(`HTTP ${resp.status}: ${text}`);
}

const data = await resp.json();
console.log(data.choices?.[0]?.message?.content);

Possible settings

note

General settings for all scrapers

Parameter name	Default value	Description
Listen Host	127.0.0.1	IP address or hostname of the interface on which the service accepts inbound connections
Listen Port	3000	Port number on which the service accepts inbound connections
FreeAI::ChatGPT preset	default	Preset for FreeAI::ChatGPT scraper
FreeAI::Copilot preset	default	Preset for FreeAI::Copilot scraper
FreeAI::DeepAI preset	default	Preset for FreeAI::DeepAI scraper
FreeAI::GoogleAI preset	default	Preset for FreeAI::GoogleAI scraper
FreeAI::Kimi preset	default	Preset for FreeAI::Kimi scraper
FreeAI::Perplexity preset	default	Preset for FreeAI::Perplexity scraper