What we don’t do
No training on your data
Your prompts and completions are never used to train or fine-tune any model, Deepshi’s or anyone else’s.
Our own models
Deepshi’s own models run on private infrastructure that Deepshi operates. Your prompts stay within Deepshi’s own stack and are never handed to anyone else to serve them.Third-party models
When you call a model created by another provider, your request is processed only to generate the response, and Deepshi uses privacy-preserving configurations so that your data is not used to train the provider’s models. Where a provider’s policy doesn’t guarantee that, your Deepshi account and identity are never sent upstream. The provider sees the request, not who you are.How requests are handled
- All traffic travels over HTTPS/TLS.
- Requests are processed for inference only.
- Operational metadata (authentication, usage metering, billing, and abuse prevention) is processed to run the service. This is separate from your prompt and completion content.