Ask HN: Would you pay for an AI API that guarantees zero prompt retention?

i am just tired of looking for a reliable open-source model AI API with ZDR and don't even save my prompts. I'm thinking of a service for people like me who want to use it.

idea is a simple OpenAI-compatible API:

Access to open-weight models

zero retention of prompts and completions

no training on data

only retain metadata required for billing and operations: request ID, model, input/output token counts, latency, timestamp, etc.

no request/response in logs

Just here to check interest. I am not 100% sure if I can get compute to do it or not (may be i can just try with my 5090 first with a small model), but I just want to check and talk with people rather than just thinking in my head.

3 points | by mhrnik 1 hour ago

2 comments

  • selfhoster11 44 minutes ago
    Tinfoil etc offer TEE inference that works well, directly or via API routers.
    [-]
    • mhrnik 34 minutes ago
      thanks. tinfoil [dot] sh looks promising. trying it.
  • cregy 1 hour ago
    Openrouter offers that already on a few models
    [-]
    • mhrnik 1 hour ago
      Tried and not reliable.

      last day only I visited to try qwen3.8-max, and there is only one provider alibaba and personally I don't prefer them.

    • minimaxir 1 hour ago
      Specifically, you can set an account setting "only do ZDR" and it will error if you try to use an endpoint that doesn't do it.