What You Get
Automatic LLM Metering
Every request routed through the gateway is metered by model, token count, and cost. No manual instrumentation — just point your traffic and go.
Per-User Cost Attribution
Each request is tied to a specific user, agent, or team wallet. Know exactly who is spending what, down to the individual API call.
Multi-Provider Support
Route traffic to OpenAI, Anthropic, DeepSeek, xAI, and any OpenRouter-compatible provider through a single gateway endpoint.
Atomic Settlement
Each LLM call settles against the user's wallet via x402 in real time. No batched invoices, no reconciliation — credits go down, you get paid.
Zero-Code Integration
Point your API traffic through the gateway with a single base URL change. No SDK required — works with any HTTP client or LLM library.
Real-Time Analytics
Monitor request volume, cost per model, and per-user spend in real time. All data flows directly into the Waterfall dashboard.