Tools / AI
Content Moderation $0.002 / call
Safe/unsafe classification with categories.
GET /v1/moderateClassifies text for safety using Llama Guard and returns a safe flag plus any triggered category codes (hate, violence, self-harm, and more). For agents processing user-generated content.
Parameters
text required | Text to classify (max 12000 chars) |
Example
macOS / Linuxcurl -s "https://quartermaster.surewhynot.app/v1/moderate?text=I%20love%20sunny%20days"curl.exe -s "https://quartermaster.surewhynot.app/v1/moderate?text=I%20love%20sunny%20days"Unpaid, these return 402 Payment Required with the payment details in the header (add -i to see them). curl.exe ships with Windows 10+ and works in cmd and both PowerShell versions. To actually pay, use an x402 client (see Connect) or call it as the MCP tool. Cost: $0.002 per call.
FAQ
What categories does it check?
The Llama Guard taxonomy: violent and non-violent crimes, hate, self-harm, sexual content, privacy, and more — each returned as a code with a human-readable name.
How do I pay for this endpoint?
Call it with no payment and you receive HTTP 402 with machine-readable payment requirements. Attach a USDC payment on Base with any x402 client (for example @x402/fetch) and retry — the whole loop is two requests. This call costs $0.002 in USDC.
Do I need an account or API key?
No. There are no accounts, logins, or API keys anywhere in Quartermaster. Payment is per call over the x402 protocol; your wallet is your identity.
Can I call this as an MCP tool instead?
Yes. Quartermaster is also an MCP server at /mcp, so any MCP client (Claude Code, Claude.ai, Cursor) can mount this tool. See /connect for setup.