How the Ambra inference API handles the data sent to it. In short: prompts and completions are processed in memory and never stored, and nothing is used for training.
- Prompt and completion retention
- None. Content is held in memory for the life of the request only.
- Training on customer data
- Never.
- Request logging
- Metadata only: timestamps, token counts, model, status and latency.
- Processing region
- North America.
- Encryption in transit
- TLS on every connection to the API.
- Subprocessors
- RunPod (compute), Cloudflare (network edge). Stripe for billing only, never request content.
- SOC 2
- No report yet.
- Security and privacy contact
- contact@ambracompute.com
Documents
Data PolicyZero data retention, no training, what we record, where requests run and who our subprocessors are.Read →Privacy PolicyThe personal information we collect through the API and this website, and your rights over it.Read →Terms of ServiceThe terms for using the Ambra inference API and this website.Read →
Last updated 13 November 2026
