MModelTrust

Verification console

Check an AI endpoint.

Submit an OpenAI-compatible endpoint. The current build performs one real connectivity and latency test; deeper capability tests are present as explicit placeholders.

Current scope

  • ✓ Public HTTPS endpoints only
  • ✓ OpenAI-compatible chat completions
  • ✓ One bounded request with a 20s timeout
  • — No identity claim or overall score yet

Secret handling boundary

Your key is sent only to the ModelTrust server for this verification. It is never stored, logged, included in analytics, or returned in the report.

The current version makes one minimal chat-completions request. Estimated provider usage: under 20 tokens.