Receipt
Modelgpt-4.1
Tokens in1,200
Tokens out340
Cost$0.004180
Price listrpl-2026-06-01
Basismeasured
Live in about ten minutes.
- Create a workspace keyShown once, stored hashed.
- Connect your provider keyOpenAI or Anthropic, probed then sealed.
- Point your base URL at RecoveaOne line in your existing client.
Admission runs before your provider does.
- AuthenticateUnknown key, 401.
- ThrottleOver your limit, 429.
- CapArmed cap, 402. Nothing forwards.
- ForwardUnsealed in memory.
- PriceAgainst a frozen price list.
- ReceiptOne row, hash-chained.
Exact contract in the caps documentation.
Cost lands as the call returns.
Priced and attributed by key, project and route. Nothing to instrument.
ScopeWorkspace
Monthly cap150.00
Spent31.05
A cap answers the request itself.
Alerts are not caps. Arm a ceiling; admission refuses over it, before your provider is contacted.
Monthly cap150.00
Both answer error.code: budget_exceeded. Branch on the code, not the status.
- Status
- 402
- 429 with Retry-After
- Error type
- insufficient_quota
- rate_limit_error
- Error code
- budget_exceeded
One row you can check without us.
Every call writes a hash-chained receipt. Re-derive it yourself. One row per request.
See the proofparamnull
The limits, said plainly.
Designed to fail open: if the gateway degrades, traffic goes straight to your provider. The only stop is a cap you armed.
Your provider keys stay yours: sealed, bound to your workspace, never written to a log.