—

Multi-model AI API gatewaywith prepaid credits.

ProxyStacks Relay is an independent AI API gateway for developers. Buy service credits, use one OpenAI-compatible endpoint, and meter token usage across managed model routes—with keys, logs, and rate limits included.

Start free View docs

Unified API gateway

Prepaid credits

Usage & cost logs

relay.dispatch

curl https://proxystacks.com/v1/chat/completions \
  -H 'Authorization: Bearer sk-relay-••••••••' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "relay-mini",
    "messages": [
      { "role": "user", "content": "Hello, Relay." }
    ],
    "stream": true
  }'

200 OK

model

relay-mini

response

Hello! Relay is ready
to route your request.

tokens

latency

624ms

Chat + Responses

Standard API surfaces

Per-token billing

Usage ledger

Prepaid credits

Predictable spend

Self-serve

Subscribe & cancel

Chat Completions

compatible

Responses API

compatible

Anthropic Messages

compatible

What you are buying

Gateway access and metered credits—not vendor accounts.

Plans add prepaid Relay service credits. Each request deducts credits at published token rates. You get developer tools—API keys, usage logs, and limits—on top of a multi-model gateway. You do not receive upstream provider accounts or official reseller rights.

Create a Relay API key

Call one multi-model gateway

Send requests to Relay Mini, Standard, or Advanced routes through OpenAI-compatible APIs. We route to managed backend capacity.

Meter every request

Token counts, status, latency, and cost are deducted from your credit balance and shown in the dashboard ledger.

Start free, then pick a monthly credit plan.

Paid subscriptions and credit packs are processed by Waffo Pancake as merchant of record and can be managed from your dashboard.

View pricing