The local LLM gateway.
Your keys. Your machine. Your tokens.
Token Guard is the only LLM cost monitor that cannot see your prompts. No cloud, no SDK, no extra hop. Track every token and stop surprise bills — nothing leaves your computer.
macOS · Windows · Linux
Cannot see your prompts
The proxy runs on your machine. Your prompts stream straight to the provider — never through a third-party server.
Zero added latency
No extra network hop. The request path is identical to calling the provider directly, so SSE streams arrive byte-for-byte as sent.
Keys in the OS keychain
API keys live in Windows Credential Manager, macOS Keychain, or Linux Secret Service. Your code never touches them.
One env var. Done.
Point any OpenAI-compatible client at Token Guard and keep using the models you already pay for.
OPENAI_API_KEY=dummy
| Token Guard | Cloud gateways | Self-host (LiteLLM) | |
|---|---|---|---|
| Can see your prompts | Cannot | Can | Can |
| Extra network hops | 0 | 2 | 1 |
| Setup | 1 env var | SDK + account | Docker + Python |
| Where keys live | OS keychain | Their cloud | Server env |
| Native tray app | Yes | No | No |
Ready to stop surprise bills?
Download the free edition from GitHub, or buy the paid edition for direct downloads and automatic updates.