RudraTech API

Powerful, flexible, and easy-to-use API for deploying AI models at scale. RESTful endpoints with SDKs in Python, Node.js, and Go.

API Features

Fast & Scalable

Sub-100ms latency with auto-scaling to handle millions of requests

Enterprise Security

End-to-end encryption, SOC2 compliance, and granular API access controls

Multiple SDKs

Official SDKs for Python, Node.js, Go, and TypeScript with full type support

Global Regions

Deploy in US, EU, APAC with automatic load balancing and failover

Streaming Support

Real-time streaming responses for low-latency applications

Rate Limiting

Flexible rate limiting and quota management for your use case

Quick Start Example

JavaScript / TypeScript
import { Rudra } from '@rudratech/sdk';

const rudra = new Rudra({
  apiKey: process.env.RUDRA_API_KEY,
});

// Generate predictions with LLM Platform
const response = await rudra.llm.generate({
  model: 'gpt-4-turbo',
  prompt: 'Explain quantum computing',
  temperature: 0.7,
});

console.log(response.text);

API Endpoints

POST

/v1/llm/generate

Generate text using language models

POST

/v1/embeddings/create

Create embeddings for semantic search

POST

/v1/vector/search

Search vectors in our database

GET

/v1/models

List available models

POST

/v1/inference/batch

Run batch inference jobs

GET

/v1/jobs/{id}

Get job status and results

Simple, Transparent Pricing

Pay only for what you use. First 1 million tokens are free every month.