LLMCap – A proxy that hard-stops LLM API calls when you hit a dollar cap

cfaruk1 pts0 comments

LLMCap — Hard Dollar Caps on LLM API Calls<br>5 providers · on every LLM call.<br>When you hit $50, it stops. Not an alert — it stops . One line of code change.<br>No surprise bills. Ever.<br>Start 3-Day Trial — $0See How It Works

your_app.py<br># Before<br>client = Anthropic(api_key="sk-ant-...")

# After — one line change<br>client = Anthropic(<br>api_key="sk-ant-...",<br>base_url="https://proxy.llmcap.io/anthropic"<br># When you hit $50 → 429. Token never consumed.

Works with every major provider

Anthropic

OpenAI

Google Gemini

Mistral

Cohere

Setup in 5 minutes<br>How LLMCap works

01<br>Change base_url<br>Point your API client at proxy.llmcap.io. Works with every SDK. No code changes beyond that one line.

02<br>Set your cap<br>Define daily, monthly, or per-key dollar limits in the dashboard. Per-model granularity supported.

03<br>🛡<br>Sleep peacefully<br>When a cap is hit, LLMCap returns 429 before the token is consumed. No charge. No surprise bill.

Providers supported

0ms<br>Avg added latency

18,742<br>Requests blocked today

0.9%<br>Uptime

Available everywhere you code<br>Works in your workflow

Marketplace<br>VS Code Extension<br>Live spend in your status bar. Click to see today's usage, burn rate, and blocked count — without leaving the editor.

Install Extension<br>>_<br>PyPI<br>Terminal CLI<br>Check spend, browse logs, and manage keys from the command line. Works on macOS, Linux, and Windows.

pip install llmcap<br>View on PyPI<br>🪟<br>Desktop<br>Windows Tray App<br>System tray icon shows live spend. Right-click for stats and quick actions. Always visible, never intrusive.

pip install "llmcap[tray]"<br>Get Tray App

LLMCap · Hard caps · No surprise bills · LLMCap · Hard caps · No surprise bills · LLMCap · Hard caps · No surprise bills · LLMCap · Hard caps · No surprise bills · LLMCap · Hard caps · No surprise bills · LLMCap · Hard caps · No surprise bills · LLMCap · Hard caps · No surprise bills · LLMCap · Hard caps · No surprise bills ·

Simple pricing<br>Pick your plan<br>3-day trial, no charge until it ends · Cancel anytime

Starter<br>$19/mo<br>after 3-day trial

✓2 API keys<br>✓All 5 providers<br>✓Daily & monthly caps<br>✓30-day audit log<br>✓1 user<br>✓Email support<br>Start 3-Day Trial<br>MOST POPULAR<br>Pro<br>$49/mo<br>after 3-day trial

✓Unlimited API keys<br>✓All 5 providers<br>✓Per-key & per-model caps<br>✓90-day audit log<br>✓Up to 5 users<br>✓Priority support<br>Start 3-Day Trial

Credit card required for trial. Cancel before day 3 and you won't be charged.

Questions

Does LLMCap ever see or store my API keys?+<br>No. Your provider API key (e.g. sk-ant-...) is passed through the proxy header on each request and immediately discarded. LLMCap only stores your LLMCap proxy key, hashed with bcrypt. We never log your provider keys.

Does it work with streaming responses?+<br>Yes — streaming is supported from day one. LLMCap passes SSE chunks through in real time. If the budget is exceeded mid-stream, the connection is closed and a final 429 event is sent. The token that triggered the cap is not charged.

What exactly happens when the cap is hit?+<br>The next incoming request is rejected with HTTP 429 before it reaches the provider. The token is never consumed, so you are never billed for it. Your app receives the same 429 response structure providers use for rate limiting, so existing error handling works as-is.

Can I self-host LLMCap?+<br>Self-hosting is on the roadmap. The proxy is open source (FastAPI + Redis). For now, the managed service at proxy.llmcap.io is the recommended path — it's already deployed with

llmcap caps hard surprise bills proxy

Related Articles