Draft — pending legal review

Data policy

What denv keeps when you call the shared inference endpoint, and what it does not.

This covers calls to the shared inference endpoint, https://api.run.denv.ai/v1.

Prompts and completions

  • denv does not store or log your prompts or completions.
  • denv does not use them for training.

What we keep

For billing, and only that, we keep for each request:

  • the number of tokens (input, cached input and output),
  • the model,
  • the id of the key that made it,
  • timestamps.

Where requests run

Requests are processed in memory on GPUs in Nebius eu-north1, in Finland.

The prefix cache

The engine keeps recent prompt prefixes briefly, in GPU memory only, so a repeated prompt is answered faster.

Payments

Card payments are handled by Stripe. Your card details never reach denv.

Questions

Email anup@justcopy.ai. See also the terms of service.