Cap the retrieval. Keep the provider key.
A retrieval-augmented generation app can loop model calls over large retrieved context against a standing provider secret. Issue a Till key for that app with a required request ceiling so remaining capacity stays readable and the pipeline can stop.
Isolate the generation traffic, not the provider account.
-
01
Issue a disposable Till key for the app
Set the request ceiling from the expected retrieval-plus-generation calls, then add optional token, estimated-spend, expiry, and IP bounds when the runtime needs a tighter envelope.
-
02
The provider credential stays behind Till
The RAG app uses a Till key, not an unconstrained provider secret in the retriever or generation process. When the app is retired, revoke or let expiry stop that key without rotating every connection.
-
03
This is not a retriever, vector store, or embedding host
Till does not chunk documents, host embeddings, or replace your search index. 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 RAG app 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 vector database, 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.
Run the retrieval. End the key.
Request Pro beta access. Till is a controlled beta; accounts are onboarded manually. Do not start from self-serve checkout.