Ctrlk
<- back to nexos.ai
For the complete documentation index, see llms.txt. This page is also available as Markdown.

ProxyAI Integration

This guide details how to integrate ProxyAI with JetBrains IDEs (IntelliJ, PyCharm, WebStorm) to enable AI-powered chat and code completions using nexos.ai models.

What is ProxyAI?

ProxyAI is an AI-powered coding assistant that integrates with JetBrains IDEs (IntelliJ IDEA, PyCharm, WebStorm, and others).

It supports OpenAI API–compatible provider configuration, allowing you to connect to any OpenAI-compatible endpoint by supplying a custom base URL and API key.

Prerequisites

  • You can use any OpenAI compatible model or assistant.

    • To check what models are available for you, call Gateway API Models You can use either nexos_model_idor id as model.

    • To check what AI agents are available for you, call Agent Management.

  • As an API URL you should use this URL: https://api.us.nexos.ai/v1/chat/completions

Install ProxyAI plugin

  1. Open Intellij IDE, go to Settings -> Plugins

  2. From top bar choose Marketplace

  3. Type ProxyAI in search bar

  4. Click Install next to the ProxyAI plugin name and wait till installation ends

    JetBrains IDE Marketplace settings showing ProxyAI plugin search result with Install button.

  5. Restart IDE

Configure ProxyAI plugin

  1. Open Intellij IDE Settings

  2. Go to Tools -> ProxyAI

    ProxyAI settings page under Tools with Display name field set to "sredni".

  3. Add Nexos provider in Providers -> Custom OpenAI

  • On the right side you can click + (Add)

  • In Provider setting section choose either OpenAI or OpenRouter

  • Put Provider name

  • Paste Nexos API key

Custom OpenAI provider setup screen with Nexos provider name and API key field.

  1. In Chat Completions tab

  • Paste API URL

  • Paste Nexos model id in Body tab

  • Click Test Connection to see if everything works

Chat Completions tab showing Nexos API URL, model ID, and successful test connection.

  1. In Code Completions tab

  • Check Parse response as Chat Completions

  • Choose Chat-based FIM as FIM template

  • Paste API URL

  • Paste Nexos model id in Body tab

  • Click Test Connection to see if everything works

Code Completions tab with Parse response as Chat Completions enabled and Chat-based FIM selected.

  1. Choose newly added Nexos model in Models for all types of requests (tip: you can add more Nexos providers with different models for different types of requests)

Models settings page showing Nexos provider selected for Chat, Auto apply, Commit messages, Inline edit, and Name lookups.

  1. Click Apply and OK

  2. Open ProxyAI chat window and ask anything about your code.

ProxyAI chat window in JetBrains IDE showing default welcome message and prompt input field.

FAQ

Which other integrations are available in nexos.ai Gateway?

nexos.ai Gateway supports integrations with the following coding tools:

PreviousStreamlit
NextLangfuse

Last updated