What is zero data retention (ZDR)?

Zero data retention (ZDR) is the claim that an AI endpoint does not keep the prompt, the completion, or other residue of a request after the call finishes.

Together AI serverless default zero data retention: terms and exceptions

Q: What is the ZDR score for Together AI serverless default?

On zdr.dev the published score is ZDR 0.5 (x) · C. No storage by default ('supports ZDR'); training/storage opt-in. Passthrough models forward to upstream policies; no serverless region selection.

ZDR 0.5 (x) · C

Short answer

No storage by default ('supports ZDR'); training/storage opt-in. Passthrough models forward to upstream policies; no serverless region selection.

Scope and evidence

Provider	Together AI
Service	serverless default
Lane	ZDR
Origin	US United States
License	open-weight
Hosting	Self-host
Score	ZDR 0.5 (x) · C Architectural ZDR. Nothing durably written by provider; stateful features blocked/rejected; still third-party plaintext processing
Evidence	Marketing or support claims (C: marketing or support-article claims)
Source-review date	2026-08-24 (registry)

Other lanes for Together AI

ZDR 0.5 (x) · Ctogether/api · serverless defaultZDR

Structured breakdown

Default posture: no storage by default ('supports ZDR'); training/storage opt-in
Exceptions and carve-outs: passthrough models forward to upstream policies; no serverless region selection

Approval and setup path

default posture; contractual promise requires enterprise agreement

Flags on this record

x: subprocessor exposure

Practical questions for your agreement

Does your signed agreement cover this exact service, model set, and feature path?
Which retention, logging, and human-review exceptions still apply after any ZDR election?
What configuration evidence (flags, project settings, store defaults) confirms the posture you expect?
Do your customer commitments match what the reviewed evidence supports?