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.deepseek- go to DeepSeek, such as deepseek-chat and deepseek-reasoner. Hugging Face’s deepseek-ai/ ids are the exception: they go to Hugging Face.
DeepSeek speaks OpenAI’s wire format, so PromptGuard forwards your request to api.deepseek.com/v1 as you sent it and returns DeepSeek’s reply unchanged. Any OpenAI client works.
Authorization on every request.
Auto-instrumentation
DeepSeek has no SDK of its own; DeepSeek’s docs use the OpenAI client. Pointed atapi.deepseek.com, that client is the openai package, which auto-instrumentation patches, so init() scans those calls too.