Skip to main content

Proxy

Proxy Base URL: https://api.promptguard.co/api/v1Point your LLM SDK’s base_url / baseURL to this endpoint. Your existing provider API key goes in the Authorization header as usual; add your PromptGuard key via X-API-Key.
Groq is checked before Hugging Face and OpenAI, so it gets every model id starting llama-3, llama-4, llama3-, meta-llama/, qwen/, qwen-, openai/, moonshotai/, canopylabs/, whisper-, distil-whisper-, playai-, groq/, gemma or mixtral-. That includes meta-llama/ and qwen/ ids you may have meant for Hugging Face. Groq speaks OpenAI’s wire format, so PromptGuard forwards your request to api.groq.com/openai/v1 as you sent it and returns Groq’s reply unchanged. Any OpenAI client works.
Groq keys cannot be stored as provider keys yet, so send yours in Authorization on every request.

Auto-instrumentation

The SDKs do not patch groq. Python’s init() names it in its startup warning when it is installed, so you know its calls are not scanned. Use the proxy.