Cap the batch. Keep the provider key.
A classify, embed, or rewrite job can keep calling a standing provider secret after the queue is empty. Issue a Till key for that run with a required request ceiling so remaining capacity stays readable and the batch can stop.
Isolate the batch traffic, not the provider account.
-
01
Issue a disposable Till key for the run
Set the request ceiling from the expected items, then add optional token, estimated-spend, expiry, and IP bounds when the worker needs a tighter envelope.
-
02
The provider credential stays behind Till
The batch worker uses a Till key, not an unconstrained provider secret in the job process. When the run is retired, revoke or let expiry stop that key without rotating every connection.
-
03
This is not a batch runtime or job queue
Till does not enqueue items, retry workers, or replace your orchestrator. It is a hosted control layer in front of 12 AI providers: a required request ceiling and optional token, spend, expiry, and IP controls.
-
04
Pro: $59/month, 25 scoped keys, 25,000 monthly activations
Those are plan limits. Public signup is closed; request Pro beta access. Provider inference is billed by the provider. Till charges a platform subscription.
Connect provider accounts once. Each batch job gets a disposable Till key with a required request ceiling and optional token, estimated-spend, expiry, and IP controls. Till is not a zero-knowledge vault, a job queue, or a replacement for provider billing or IAM.
These are plan limits, not usage claims.
Pro
Scale
Public anonymous signup is closed. New accounts are approved and provisioned manually. Existing customers can open the dashboard. Compare the full ledger on pricing.
Finish the queue. End the key.
Request Pro beta access. Till is a controlled beta; accounts are onboarded manually. Do not start from self-serve checkout.