Redact, call your model, restore — one request
Takes an OpenAI-shaped chat request, redacts it, forwards it to your own model vendor using the key in X-Provider-Key, and restores the real values in the reply. Your provider key is forwarded to that one call and never stored. OpenAI-compatible, so an existing client needs only a new base URL.
post/proxy/chat/completions
Request
- Base URL: https://secureai.one/v1
- URL: https://secureai.one/v1/proxy/chat/completions
- Auth: HTTP bearer
Headers
X-Provider-Keystring required
Your own model vendor's API key. Forwarded, never stored.
X-Provider'anthropic' | 'openai' | 'google'
Which vendor, when the model name does not say. One of anthropic, openai, google.
Request body
Response
An OpenAI chat completion, with real values restored
Changes
No recorded changes to this operation across all 1 revision of this API.