01
Create an API key
Sign in, create a key, and keep the full value somewhere secure—it is shown only once.
Ship AI featureswithout provider lock-in.
One OpenAI-compatible endpoint. Switch between available models, track spend, and keep one client integration.
OpenAI-compatible
Usage and cost logs
Multiple API surfaces
relay.dispatch
curl https://proxystacks.com/v1/chat/completions \
-H 'Authorization: Bearer sk-relay-••••••••' \
-H 'Content-Type: application/json' \
-d '{ "model": "deepseek-chat", "messages": [ { "role": "user", "content": "Hello, Relay." } ], "stream": true }'
200 OK
model
relay-mini
response
Hello! Relay is ready
to route your request.
tokens
37
latency
624ms
Chat + Responses
Compatible APIs
Per request
Usage ledger
Monthly credits
Predictable billing
Self-service
Subscription portal
Chat Completions
compatible
Responses API
compatible
Anthropic Messages
compatible
What you are buying
A hosted software gateway—not a consumer proxy network.
Relay gives developers authenticated access to configured AI model providers through compatible API endpoints. Your plan adds service credits; each API call deducts credits according to its measured token usage and published rate.
02
Use one base URL
Point compatible clients to proxystacks.com and choose from the models currently enabled for your account.
03
Track every request
Review token counts, request status, latency, and cost from the dashboard usage ledger.
Start free, then choose a published monthly plan.
No card is required for the free tier. Paid subscriptions are processed by Creem as merchant of record and can be managed or canceled from your dashboard.