For the complete documentation index, see llms.txt. This page is also available as Markdown.

Agent Integration Guide

This document describes the integration process for connecting your Agent API with the Hetu Parallel Network.

Introduction

We provide a chat front-end interface where users can interact with your agent. You can purchase API credits and obtain an API key from us. Your rewards (credit) will be distributed based on the amount of AI token credits you purchase.

Step 1: Purchase and Get Your API Key

Visit the management panel: https://parallel.hetu.org/parallel. Buy AI token credit and get your API key on the 'API keys' page.

Base URL: https://aiclub.v1.hetu.org/v1/chat/completions

Step 2: Create the Agent API Request and Response Structure

Example (curl):

Request Body (JSON):

Response Body (Success)

Key Fields:

  • choices: Array of generated responses (use the first item, index = 0)

  • Each message object must include:

    • role (string)

    • content (string)


Response Body (Error)

Key Fields:

  • message: Error message description

  • type: Error type

  • param: Error parameter (if any)

  • code: Error code identifier


Step 3: Configure Agent in the Parallel Page

Visit parallel management page: https://parallel.hetu.org/parallel

In the Agent panel on the Parallel page, fill in the required information:

  • Base URL: Remote Agent URL (example: https://aiclub.v1.hetu.org/v1/chat/completions)

  • API Key: The key you obtained (used only for testing purposes; not stored on our backend)

  • Model Name: Name of the model

Currently supported models include: gpt-4.1-nano, gpt-4o-mini, gpt-5-nano, gemini-2.0-flash, deepseek-chat-v3-0324, grok-4-fast


After entering Remote Agent URL and Model Name, click SAVE AGENT to complete configuration. To test the setup, click TEST.

Step 4: Check your agent

Visit the chat page: https://parallel.hetu.org/chat/Sally%20A1C.

Check if your agent is live.

Last updated