{
  "_comment": "Data-retention / logging / ZDR posture per hosted gateway and first-party model cloud, from primary sources (official docs, privacy policies, DPAs). Answers 'who sees/logs/trains on my prompts through this gateway?'. Self-hosted gateways are omitted: you own the data plane, so retention is whatever you configure. 'not documented' = the official docs are silent, NOT 'no'. On every router, real exposure is set by the UPSTREAM you route to, not just the router's own policy — enable a ZDR-only / no-training-providers filter, don't just trust the router. Verify against live policy before an audit.",
  "as_of": "2026-07-08",
  "legend": {
    "logs_bodies_by_default": "does it store prompt+completion bodies by default? yes | no | configurable | not documented",
    "zdr": "zero-data-retention / no-log mode: default | opt-in (self-serve) | approval-gated | none | not documented",
    "trains_on_prompts": "does the operator train on your prompts? no | opt-out | upstream-depends | yes-by-tos | not documented (routers: 'own' policy vs 'upstream')",
    "retention": "stated retention of prompt/response bodies"
  },
  "gateways": [
    {"name": "Cloudflare AI Gateway", "type": "hosted", "logs_bodies_by_default": "yes", "zdr": "opt-in (self-serve opt-out; no formal ZDR mode)", "trains_on_prompts": "not documented", "retention": "storage-limit based (Free 100k logs/acct, Paid 10M/gateway), no time period", "caveat": "Bodies persist by default — you must opt out (`cf-aig-collect-log-payload: false`); no documented ZDR guarantee or training statement.", "sources": ["https://developers.cloudflare.com/ai-gateway/observability/logging/", "https://developers.cloudflare.com/ai-gateway/reference/limits/"]},
    {"name": "Portkey (cloud)", "type": "hosted", "logs_bodies_by_default": "yes", "zdr": "opt-in (self-serve `x-portkey-debug:false`; full 'nothing stored' is sales-gated)", "trains_on_prompts": "not documented", "retention": "3d free / 30d Production / custom Enterprise", "caveat": "Self-serve toggle suppresses log payloads; the strongest 'nothing stored' guarantee is enablement-on-request.", "sources": ["https://portkey.ai/docs/introduction/what-is-portkey", "https://portkey.ai/pricing"]},
    {"name": "Vercel AI Gateway", "type": "hosted", "logs_bodies_by_default": "no", "zdr": "default (own layer); enforce upstream-ZDR via toggle/per-request", "trains_on_prompts": "no (own); upstream opt-in filter (`disallowPromptTraining:true`)", "retention": "0d at gateway layer; upstreams vary", "caveat": "'ZDR by default' = Vercel's own handling only; requests can still hit non-ZDR upstreams unless you enable the filters. Team-wide ZDR + training controls launched 2025-26.", "sources": ["https://vercel.com/docs/ai-gateway/security-and-compliance/zdr", "https://vercel.com/docs/ai-gateway/security-and-compliance/disallow-prompt-training"]},
    {"name": "Helicone (cloud)", "type": "hosted", "logs_bodies_by_default": "yes", "zdr": "none (branded); omit headers `Helicone-Omit-Request/Response:true`", "trains_on_prompts": "not documented", "retention": "7d free / 1mo Pro / 3mo Team / configurable Enterprise", "caveat": "It's a logging proxy — stores bodies by default. Retention numbers live only on the pricing page; binding legal docs are 2023-24 vintage and silent on LLM data/training.", "sources": ["https://docs.helicone.ai/features/advanced-usage/omit-logs", "https://www.helicone.ai/pricing"]},
    {"name": "Requesty", "type": "hosted", "logs_bodies_by_default": "no", "zdr": "default (self-serve)", "trains_on_prompts": "no (own); upstream opt-in per project", "retention": "0d default; 30d encrypted (EU) if logging enabled; upstreams vary", "caveat": "Router defaults to no body storage, but enabling logging or routing to a retaining upstream means prompts persist downstream.", "sources": ["https://www.requesty.ai/security", "https://www.requesty.ai/privacy/subprocessors"]},
    {"name": "OpenRouter", "type": "hosted", "logs_bodies_by_default": "no", "zdr": "opt-in (self-serve: global / per-model-group / per-request `zdr:true`)", "trains_on_prompts": "no (own); upstream-depends — some free-tier routes train", "retention": "0d unless prompt-logging opted in; upstream shown per-endpoint", "caveat": "Opt-outs govern WHICH upstreams get data, not what they do — verify the specific endpoint; free-tier routes can still train. Policy actively maintained (updated 2026-07-06).", "sources": ["https://openrouter.ai/privacy", "https://openrouter.ai/docs/guides/features/zdr"]},
    {"name": "Eden AI", "type": "hosted", "logs_bodies_by_default": "no", "zdr": "default", "trains_on_prompts": "no (own); upstream = customer's responsibility", "retention": "not retained after processing (only billing/security metadata)", "caveat": "ZDR covers Eden AI's own layer only; the chosen upstream's practices are separate and explicitly excluded from Eden AI's responsibility.", "sources": ["https://www.edenai.co/privacy", "https://www.edenai.co/dpa"]},
    {"name": "Martian", "type": "hosted", "logs_bodies_by_default": "not documented", "zdr": "not documented", "trains_on_prompts": "yes-by-tos", "retention": "not documented ('as long as you use our Services')", "caveat": "⚠️ Public ToS defines 'Customer Materials' to include your Input Data and grants Martian a license to use it 'to train and improve Martian's models' — no documented opt-out or ZDR toggle; only relief is a negotiated DPA. Do not send sensitive prompts without one.", "sources": ["https://www.withmartian.com/terms-of-service", "https://withmartian.com/privacy-policy"]},
    {"name": "Azure OpenAI", "type": "first-party", "logs_bodies_by_default": "configurable (only human-review-flagged content stored)", "zdr": "approval-gated (Modified Abuse Monitoring; Limited Access form)", "trains_on_prompts": "no (not used to train foundation models; not shared with OpenAI)", "retention": "no fixed day-count on current pages (the previously-documented 30-day figure is gone)", "caveat": "⚠️ CHANGED 2025-26: rebranded 'Foundry Models sold by Azure' (Oct 2025); the '30 days' figure is no longer stated — storage now conditional on abuse-flagging, ZDR via approval only.", "sources": ["https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/abuse-monitoring", "https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy"]},
    {"name": "AWS Bedrock", "type": "first-party", "logs_bodies_by_default": "no", "zdr": "config via API (`data_retention_mode: none`)", "trains_on_prompts": "no (providers can't access prompts/completions); except opt-in `provider_data_share` models", "retention": "0d default; up to 30d if `provider_data_share`; your own logs persist until deleted", "caveat": "New 2025-26 retention-mode system; some newer models REQUIRE `provider_data_share` and are blocked under `none` — ZDR and model access can conflict per-model.", "sources": ["https://docs.aws.amazon.com/bedrock/latest/userguide/model-invocation-logging.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html"]},
    {"name": "Google Vertex AI", "type": "first-party", "logs_bodies_by_default": "configurable (⚠️ standard non-invoiced accounts ARE logged for abuse monitoring)", "zdr": "opt-in / enterprise-gated (disable caching + invoiced billing; DPA amendment)", "trains_on_prompts": "no (not used to train foundation models without permission)", "retention": "abuse logs up to 90d; default I/O caching up to 24h; 0d under full ZDR config", "caveat": "The permissive default is for enterprise/invoiced accounts; standard GCP-ToS accounts WITHOUT invoiced billing get prompts logged (up to 90d) unless they file the opt-out form, and caching must be disabled separately.", "sources": ["https://cloud.google.com/vertex-ai/generative-ai/docs/data-governance", "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/abuse-monitoring"]},
    {"name": "OpenAI (direct API)", "type": "first-party", "logs_bodies_by_default": "yes (30-day abuse monitoring)", "zdr": "approval-gated (via sales; then `store` is always false)", "trains_on_prompts": "no (API data not used to train, since 2023-03-01, unless you opt in — differs from ChatGPT consumer)", "retention": "30d default; 0d with approved ZDR — but see caveat", "caveat": "⚠️ NYT v. OpenAI preservation order (May 2025, affirmed Jun 2025, narrowed Sep 2025) forces OpenAI to PRESERVE output-log data — including API content normally deleted at 30d — under legal hold. Not reflected in the standard data-usage doc; the '0/30-day' deletion promise is currently subject to a litigation override for affected data.", "sources": ["https://developers.openai.com/api/docs/guides/your-data", "https://openai.com/index/response-to-nyt-data-demands/"]}
  ]
}