For every agent to hold its own token and its own monthly ceiling, never a shared key.
To check spend before each request forwards to OpenAI or Anthropic, not after the invoice.
Frozen the moment a loop runs away — one agent, or a batch, never the whole fleet.
Agents call Tollgate instead of calling OpenAI or Anthropic directly. Every request is checked against that agent's budget before a dollar leaves. Overspend is prevented, not reported back to you a month later.
Pulling a shared API key takes down every agent using it. Tollgate freezes the one that is misbehaving, and the next request it sends comes back denied.
Select any number of agents and freeze them together. The rest of the fleet keeps running on its own tokens.
A soft freeze lets in-flight work finish. A hard freeze denies the next request outright. Both are one click.
Freezing flips a Redis flag the proxy already reads. There is no deploy, no key rotation, and no downtime for anything else.
Cost is metered from the provider's own usage numbers, not estimated. Every request lands in an audit log with the agent, assistant, model, token count, and what it cost — including the ones that were turned away.
| When | Agent | Assistant | Model | Status | Tokens | Cost |
|---|---|---|---|---|---|---|
| 14:02:11 | checkout-bot | openai | gpt-4o | Allowed | 1,204 | $0.011 |
| 14:02:09 | research-bot | anthropic | claude-sonnet-4 | Allowed | 8,410 | $0.084 |
| 14:02:04 | agent-scraper | openai | gpt-4o | Over budget | — | — |
| 14:01:58 | checkout-bot | openai | gpt-4o | Allowed | 912 | $0.009 |
Not a mockup or a video. This is the same Agent Dashboard component the product ships, running against a simulated traffic feed. Start the traffic and watch a budget fill.
Your group of agents, all managed in one place.
For larger fleets, custom limits, or self-hosting, send us a note below.