Cap the chat. Keep the provider key.
A customer or internal chatbot can burn through a standing provider secret. Issue a Till key for that deployment with a required request ceiling so remaining capacity stays readable and a runaway conversation can stop.
Isolate the chat traffic, not the provider account.
-
01
Issue a disposable Till key for the bot
Set the request ceiling from the expected conversation volume, then add optional token, estimated-spend, expiry, and IP bounds when the deployment needs a tighter envelope.
-
02
The provider credential stays behind Till
The chatbot uses a Till key, not an unconstrained provider secret in the bot runtime. When the deployment is retired, revoke or let expiry stop that key without rotating every connection.
-
03
This is not a chatbot platform
Till does not host conversations, moderate users, or replace your bot framework. 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 chatbot deployment 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 conversation host, 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.
Ship the bot. End the key.
Request Pro beta access. Till is a controlled beta; accounts are onboarded manually. Do not start from self-serve checkout.