Token Relay Access · Lower cost for top AI models

Token Relay Service

We've gathered Token providers worldwide to bring you the biggest discounts

Use GPT-4, Claude, Gemini and other top AI models at lower prices with unified management, auto failover, and real-time stats

What is a Token Relay Provider?

A token relay provider (API Relay) is a third-party API proxy service that offers the same AI model capabilities at lower prices through aggregated purchasing and optimized routing.

Lower Cost
Compared to official APIs, relay providers typically offer lower rates, some as low as 50%-80% of official pricing
Unified Interface
Most relay providers are OpenAI API compatible, seamlessly integrating with AIGateway
Multi-Model Access
One API Key to access GPT-4, Claude, Gemini and more — no separate registrations needed
Important Notes
Relay providers are third-party services. Please evaluate service quality and data security. Recommended for non-sensitive use cases
1
Register & Get API Key
Choose provider → Register & top up → Get Key and Base URL
2
Add Provider in AIGateway
Enter Base URL + API Key → Select models
3
AI Tools via Gateway
Point ChatGPT / Claude Code to local gateway

Recommended Relay Providers

The following providers are OpenAI API compatible and can be added directly in AIGateway

The above providers are community-submitted and displayed after review. AIGateway is not tied to any specific provider — any OpenAI-compatible API can be added.

Submit a Provider

Submit your recommended provider. It will be displayed in the list after review.

Base URL, must be OpenAI API compatible

Discount / referral code (optional)

Promo code expiry date (optional)

Setup Guide

Three steps to connect a relay provider — no AI tool config changes needed

1

Register with Relay Provider

Choose a provider, register and top up. Get the API Key and Base URL from the dashboard (typically like https://api.example.com/v1).

2

Add Provider in AIGateway

Open AIGateway → Providers page → Add custom provider → Enter Base URL and API Key → Select models to use.

3

Configure AI Tools

Point the API address in ChatGPT / Claude Code to the AIGateway local gateway 127.0.0.1:15721 to start using.

Example: Add relay provider

AIGateway Provider Config
# Provider Info
Name: "Relay A"
Base URL: "https://api.provider-a.com/v1"
API Key: "sk-xxxxxxxxxxxxx"
Format: "OpenAI Compatible"

# Available Models
Models:
  - "gpt-4o"
  - "claude-3-5-sonnet"
  - "gemini-pro"
  - "deepseek-chat"

Example: AI tool → gateway

Tool Config
{
  "env": {
    "OPENAI_API_KEY": "PROXY_MANAGED",
    "OPENAI_BASE_URL": "http://127.0.0.1:15721"
  }
}
API Key managed by gateway, zero exposure on tool side

Why Use Relay Providers via AIGateway?

More than just proxy forwarding — AIGateway makes relay usage safer and more flexible

Cost Comparison

AIGateway tracks token usage and costs per provider in real-time, helping you compare actual costs and make optimal choices.

Multi-Provider Failover

Add multiple relay providers to a virtual model group. When one fails or rate-limits, automatically switch to backup — no workflow interruption.

Secure Custody

All relay API keys stored in local SQLite database, never passed through third parties. AI tools don't need to expose keys.

One Config, Many Tools

Configure the relay provider once in AIGateway. ChatGPT, Claude Code, and all other tools share the same gateway entry.

Auto Format Conversion

OpenAI and Anthropic formats auto-adapted. Claude Code can directly use OpenAI-compatible relay providers.

Request Logs

Complete request logging for troubleshooting relay provider latency, error rates, and model availability.

FAQ

What's the difference between relay providers and official APIs?

Relay providers are third-party proxy services that offer lower pricing through aggregated purchasing and optimized routing. Functionally similar to official APIs, but may have latency fluctuations or availability differences. Recommended for development and non-sensitive use cases.

Is it safe to use relay providers?

Relay providers are third-party services — your request content passes through their servers. Avoid processing sensitive data (personal privacy, trade secrets) through relays. AIGateway itself does not store or forward your request content to additional servers.

How do I add a custom relay provider?

Go to AIGateway's Providers page, click "Add Custom Provider", enter the relay provider's Base URL and API Key, and select the models you want to use. Any OpenAI API compatible service can be added.

Can I use multiple relay providers at once?

Yes. Add multiple relay providers and put them in the same virtual model group with priority settings. AIGateway will call them by priority and automatically switch to backup when the high-priority provider fails (429, timeout, etc.).

Does AIGateway charge any fees?

AIGateway is open-source software under the MIT license, completely free. You only pay for the relay provider's API call costs — AIGateway itself charges nothing.

Get Started Now

Download AIGateway, connect relay providers, and use top AI models at lower cost.

Feedback