I built a LLM Gateway (think OpenRouter) that uses the new x402 protocol to allow users to pay-per-request for LLM inference calls in real-time, using dollar stablecoins.
This eliminates the need for advanced LLM users to avoid LLM Vendor specific subscriptions, API key management, billing, and vendor specific credits. Use any model you want, pay for what you use when you use it. Credits never expire.
