They watch. We stop.

Every agent runs a tab. Hit the cap, the tab closes.

Hard stop for agent fleets, not another gateway. Run the proxy on your machine. SaaS is for demo and throwaway keys.

Start a flock Read how it works

One-line proxy swap. No SDK. Solo free (3 named Agents).

Tab

tab_02c9 · research-crawler

OPEN

Spent

$0.00

of $5,000.00 hard cap

gpt-4.1 · 12,400 tok$0.31

claude-sonnet · 8,102 tok$0.19

embed-3 · 44,000 tok$0.04

reserve · pending$0.42

Closes at cap. No overage.Close tab

OpenAIAnthropicGoogleOpenRouterTogetherGroq·OpenAI-compatible endpoints·OpenAIAnthropicGoogleOpenRouterTogetherGroq·OpenAI-compatible endpoints·

The problem

A loop that retries forever spends forever. Alerts arrive after the money.

Provider budgets are monthly and shared. Dashboards report, they do not stop. By the time the alert fires, the invoice is already written.

Without FlockTab · one agent · one night

02:14 retry 1 · tool_call timeout$0.41

02:14 retry 2 · tool_call timeout$0.41

02:15 retry 3 · tool_call timeout$0.41

… 6,211 more retries

07:52 alert: budget at 80%$2,545.73

08:31 someone reads it$2,819.06

With FlockTab · cap $50.00

02:31 reserve $0.41 · blocked · capCLOSED at $50.00

How it works

Reserve. Allow or block. Close the tab.

Reserve before the call

Point the agent at FlockTab instead of the provider. Each request reserves an estimated cost against the agent's tab.

base_url = "https://proxy.flocktab.com/v1"
x-flocktab-agent: research-crawler

Allow or block, in the proxy

Cap, velocity, model and irreversible allowlists are evaluated in under a millisecond. Allowed calls pass through. Blocked calls never reach the provider.

ALLOWEDBLOCKEDFLAGGED

Close the tab at the cap

At the hard cap the tab closes. The agent gets a 402 with a reason. Reopen it by hand, on a schedule, or never.

CLOSED

What you get

Control at the wire, not a report after it.

Hard caps per agent

Daily, weekly, or per run. Caps are enforced on reservation, so the last call that would cross the line is the one that gets blocked.

research-crawler3,412.60 / 5,000

support-triage812.05 / 1,500

code-review-bot2,000.00 / 2,000

Kill switch

Close any tab, or the whole flock, from the console or one API call. Takes effect on the next reservation.

Close all tabs

Audit ledger

Every reservation, decision, and close is a line item with a reason. Export to CSV or your warehouse.

dec_8f21 · blocked · policy:cap · $0.44

Policies as code

Caps, velocity limits, model and irreversible allowlists live in a file you review like any other change. Apply per agent or per flock.

agent: research-crawler
cap:      { amount: 5000.00, window: day }
velocity: { max_calls: 120, per: minute }
models:   [gpt-4.1, claude-sonnet-4]
irreversible: []
on_cap:   close

Live decisions

Every call is a decision you can read.

The Activity view streams what the proxy decided and why. Filter by agent, policy, or outcome. Nothing is summarized away.

Activity · flocklive

14:02:35code-review-bot reserve$0.44BLOCKED

14:02:34research-crawler reserve$0.38ALLOWED

14:02:33support-triage reserve$0.12ALLOWED

14:02:31lead-enricher velocity 121/min$0.09FLAGGED

14:02:30eval-runner reserve$0.21ALLOWED

14:02:28code-review-bot cap reached$2,000.00CLOSED

Pricing

Priced per agent. Not per token.

Full pricing

Solo

Free

3 named Agents · local proxy or SaaS

Hard caps, velocity, model allowlist

14-day ledger · community

Local proxy or SaaS

Team

$19/ mo

10 included, then $2 per extra Agent

Irreversible tools, Slack, CSV

90-day ledger · email support

$2 per extra Agent after 10

Self-hosted

$0–$19/ mo

Solo or Team list. Keys stay on your machine

Local proxy on 127.0.0.1

Call-home for ledger only

Not a premium SKU

Fleet

$199/ mo from

volume · self-host preferred

SSO / SAML, multi-admin

Dedicated Slack

Air-gap on annual

Put a tab on every agent tonight.

Swap one base URL. Set a cap. Sleep.

Start a flock Talk to us