Clawgate Clawgate
Features

One gateway between Claude Code, Codex, OpenCode, and your AI spend.

Clawgate checks every request, applies your rules, and records the cost before a single token is billed. Here is everything it does.

Budgets & quotas

Hard-stop budgets that can’t be blown past

Limits are checked before each request runs, so spend simply cannot go over what you set. Cap usage per person, and set an all-time spend ceiling per project.

  • Daily & weekly token caps
  • Daily & weekly USD budget caps
  • Daily & weekly session limits
  • Max output tokens clamped per request
  • Per-project all-time budget ceiling

When a cap is hit, the request is blocked with a clear message, not a silent retry. Owners are never surprised by the cost.

If a request asks for a model you don’t allow, Clawgate quietly serves the best allowed model instead of failing. Your team keeps working, and you keep control of cost.

Model control

You decide which model runs, not the CLI

Claude Code, Codex, and OpenCode pick a model on their own, and that choice drives your cost. Clawgate puts the decision back in your hands, so you can serve lower-cost models when full power isn’t needed.

  • Forced model: pin every request to one model
  • Allowed models: whitelist what a key may use
  • Graceful substitution to the best allowed model
Smart model routing

Pay top model prices only when the work needs it

Your coding agent fires a lot of routine requests that don’t need your most expensive model. Turn on smart routing and Clawgate reads each request, judges how demanding it is, and serves the best allowed model for it, so the easy work runs on a lighter, cheaper model and your top model is saved for the hard parts. One switch, no tuning.

  • Each request is sized up by how demanding it is, not guessed by a rule
  • Routine work runs on a lighter, cheaper model; hard requests still get your strongest
  • The routing check is passed through at cost — never marked up
See how smart routing saves money →

Routing only ever picks from the models you allow, so you keep control while Clawgate quietly serves the cheapest model that fits each request.

Cost attribution

Finally know which project cost what

Every request is tied to a project and a user. No more one big number on the invoice. See exactly where the spend goes, and stop paying for side projects.

  • Per-project tracking via x-project-id
  • Per-user cost breakdown for chargeback
  • Per-model cost breakdown

Cost is tracked to the micro-dollar for each model, including separate cache rates, so the numbers are exact, not estimated.

Detailed events follow your plan’s retention (7 days to unlimited). Monthly summaries are kept for good, so your invoices and history survive even on shorter plans.

Analytics

Real-time usage you can actually act on

Track tokens, cost, latency, and sessions as they happen. Export to CSV (Team+) for your own analysis and chargeback.

  • Live usage & cost dashboards
  • Configurable retention by plan
  • CSV / usage export (Team and above)
Abuse detection

Catch misuse without reading your code

Clawgate fingerprints request content with privacy-safe hashes, never raw code, to flag suspicious patterns for your review.

  • Content mismatch: key used outside its project
  • Key sharing: one key from many IPs
  • Spikes: sudden surges in usage

Signals are scored low, medium, or high and sent to a review queue. They are never enforced automatically. You decide what to do. Scan frequency scales with your plan, up to nightly.

Prompt compression

Send less. Pay less. Same answers.

Clawgate can compress bulky tool output before it reaches the model. Old context gets squeezed, fresh work stays untouched, and accuracy holds. One switch per organization, with savings shown on your dashboard in dollars.

  • Up to 92% fewer tokens on heavy workloads
  • Recent context and model reasoning never altered
  • Adjustable strength per organization

Tokens per request on real agent workloads:

Workload Before After Savings
Code search (100 results)17,7651,40892%
SRE incident debugging65,6945,11892%
GitHub issue triage54,17414,76173%
Codebase exploration78,50241,25447%
How compression saves AI spend →

Platform fees and per-seat fees are shown clearly at billing time. The AI cost stays pure pass-through, cache savings reach you, and failed requests are never billed.

Billing & access

Transparent invoices & role-based control

Monthly invoice snapshots with per-model and per-user breakdowns. Control who can do what with roles and permissions.

  • Immutable monthly invoice snapshots
  • Role-based admin access (Team+)
  • Custom roles & audit logs (Business+)

Ready to take control?