Save up to 95% on AI costs

Smart AI Gateway with
Automatic Cost Savings

Route your AI requests intelligently, cache responses automatically, and watch your costs drop. Drop-in replacement for OpenAI API.

Get Started FreeView on GitHub

No credit card required • Open source • Self-hostable

Get Started in 60 Seconds

Drop-In Replacement

Use RELAYCOR with your existing OpenAI code. Just change the base URL and start saving.

NPM
npm install relaycor
Python
pip install relaycor
example.ts
import Relaycor from 'relaycor';

const client = new Relaycor({
  apiKey: process.env.RELAYCOR_API_KEY,
});

const response = await client.chat.completions.create({
  model: 'auto', // Smart routing
  messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(response.choices[0].message.content);
95%
Cost Savings
<100ms
Cache Response
11+
AI Models
Live Statistics

Real-time Platform Activity

Watch RELAYCOR saving costs in real-time

$0.0000
Total Saved
0
Total Input Tokens
0
Total Output Tokens
0.0
Requests/sec

Simple, Transparent Pricing

Pay only for what you use. Start with a 14-day free trial.

Trial

14 days free

5.5% markup

Simple pay-as-you-go on AI costs

  • 14-day free trial
  • Only 5.5% markup on AI costs
  • Full access to smart routing
  • Semantic caching included
  • Real-time analytics
Start Free Trial
RECOMMENDED

Production

After trial period

5.5% + 20% of savings

You only pay more when you save more

  • Everything in Trial
  • Only 5.5% markup on AI costs
  • Base fee: 20% of your savings
  • Priority support
  • Dedicated infrastructure
Start Free Trial

Example: How Much Do You Pay?

Original GPT-4 cost (1M tokens)$20.00
Cost with RELAYCOR (smart routing)$2.00
Your savings$18.00 (90%)
During Trial (14 days):
Markup (5.5% of $2.00)$0.11
Total you pay$2.11
After Trial (Production):
Markup (5.5% of $2.00)$0.11
Base fee (20% of $18.00 savings)$3.60
Total you pay$5.71

💰 You still save $14.29 (71%) compared to GPT-4!

Frequently Asked Questions

What happens after the 14-day trial?

After your trial, you automatically move to the Production plan. You'll continue to save money compared to using AI APIs directly, and we only charge based on what you actually use and save.

How is the base fee calculated?

The base fee is 20% of the money you save compared to using GPT-4 directly. If you save $100, we charge $20. This aligns our incentives - we only earn more when you save more.

Can I cancel anytime?

Yes! There are no long-term contracts. You can cancel anytime and you'll only pay for what you've used up to that point.

Everything you need to save on AI costs

Powerful features that make AI infrastructure management simple and cost-effective

Smart Routing

Automatically selects the best model for each request based on complexity, cost, and performance requirements.

Semantic Caching

Intelligent caching with 95% similarity matching. Saves costs by reusing responses to similar queries.

Cost Optimization

Real-time cost tracking and optimization. Save up to 95% compared to using GPT-4 for every request.

Self-Hostable

Your data stays with you. Run RELAYCOR on your infrastructure with full control over your data.

OpenAI Compatible

Drop-in replacement for OpenAI API. Change one line of code and start saving immediately.

Analytics Dashboard

Detailed insights into usage patterns, cost savings, and model performance across your organization.

Ready to optimize your AI costs?

Start saving money today with intelligent routing and semantic caching. No credit card required.

Get started for freeSign in
Free Tier
10,000 requests/month
No Setup
Start in 60 seconds
OpenAI Compatible
Drop-in replacement