​
Welcome to TensorOne API

The TensorOne API provides programmatic access to our decentralized AI compute platform. You can use this API to manage GPU clusters, create and deploy serverless endpoints, and interact with AI models at scale.

TensorOne API Specification

View the complete OpenAPI specification

​
Base URL

All API requests should be made to: 
https://api.tensorone.ai/v2

​
Authentication

All API endpoints require authentication using API keys. Include your API key in the Authorization header: 
Authorization: Bearer YOUR_API_KEY
You can generate API keys in the TensorOne Console under Settings > API Keys. Choose between:
  • Read: Access to retrieve data only
  • Read & Write: Full access to create, modify, and delete resources
Treat your API keys like passwords. Never expose them in client-side code or public repositories.

​
Rate Limits

API requests are rate-limited to ensure fair usage:
  • Read operations: 1000 requests per hour
  • Write operations: 100 requests per hour
  • Endpoint executions: Based on your plan

​
Response Format

All API responses use JSON format. Successful responses return the requested data, while errors follow this structure: 
{
    "error": "VALIDATION_ERROR",
    "message": "Invalid request parameters",
    "details": {
        "field": "name",
        "reason": "Name must be between 1-100 characters"
    }
}

​
Getting Started

  1. Generate an API key in the TensorOne Console
  2. Test your connection with a simple GET request to /endpoints
  3. Explore the endpoint reference below to start building with TensorOne