VibeFree privacy and AI providers

VibeFree uses two AI infrastructure providers. DeepSeek V4 Flash is the default model in web chat and the only model the VS Code extension uses; it processes prompts on DeepSeek's servers in the People's Republic of China. Llama 3.1, an optional web-chat-only model, runs on DeepInfra's US infrastructure instead.

• VibeFree does not store your prompts or the AI's responses on its own servers - only the provider that generates the response ever sees them.
• Only the content of your chat messages is sent to these providers - never your account details, credentials, or payment data.
• Media you attach (images, audio, video) is analysed by Google's Gemini API, held only for the duration of that analysis, and then deleted.
• VibeFree is continuing to evaluate moving the DeepSeek models to a UK-, EU-, or US-hosted provider.

Frequently asked questions

Which country processes my chat if I use the default model?

The People's Republic of China, via DeepSeek's own servers.

Can I choose a model processed outside China?

Yes, in the web chat: select the Llama 3.1 model, which runs on DeepInfra's US infrastructure instead of DeepSeek's. The VS Code extension always uses DeepSeek.

Where can I read the full policy?

The complete Privacy Policy covers every data processor VibeFree uses, including Cloudflare, Stripe, Resend, Google, and Idlen.