# wave Dispatch
> Local-first AI dispatch — routes each LLM request to the cheapest capable model. Bring your own
> infra and API keys (BYOK); the service only ever returns a routing decision, never your data.

## What it does
Classifies a prompt at the edge and returns which model tier should handle it (local_code,
local_search, local_summarize, direct, or escalate to your frontier model). Cuts your LLM bill by
keeping work on the cheapest capable tier.

## API
- POST /  body {"prompt":"..."}  header  Authorization: Bearer <license-key>
  -> {route, probability, margin, decided_at, forward}
- GET /transparency   data & privacy policy (append ?format=json for machine-readable)
- GET /health   -> ok
- Pay-per-use agents: a request without payment returns HTTP 402 (x402) with payment requirements.

## Pricing
- Free: 10000 routing decisions/day ($0)
- Pro: $29/mo, 100,000 decisions/day, full orchestration
- Pay-per-use: $0.0001/decision via x402 (stablecoin micropayments, no account)

## Data policy
Private by default for everyone. Your API keys, data, and inference stay on YOUR infrastructure.
We never log prompt content, your data, your keys, or model outputs.

## Links
- Home: https://wave.online
- Transparency (JSON): /transparency?format=json