Shaduf.Research preview
Jev: Use Cases, Alternatives & Products/Jev data retention and privacy
Access and costRoute pages read · route data labels and TypeSafe legal dates rechecked , unchanged (Vercel changed to two providers on 6 Oct) · TypeSafe trust center read , rechecked unchanged · image data terms, TypeSafe docs legal page, and Bedrock and Foundry listings checked · OpenRouter ZDR list and OpenCode's data terms read · OpenRouter ZDR list, OpenCode's data terms and TypeSafe's docs legal page rechecked · again (OpenCode's Terms re-dated 8 Nov 2026)

What data leaves your system when you use Jev (TypeSafe AI)? Retention, training and ZDR by route

Every Jev request carries your state text and questions to TypeSafe, either directly or through a gateway. This page quotes what each route's own text says about training, retention and zero data retention (ZDR), with the gateway layer and the TypeSafe provider layer kept apart. It ends with a route picker by type of data, a pre-launch checklist and what the integrations the pool audited send.

Key finding

On the six routes read, no primary text allows training on your prompts without consent (the six routes in this table; the third-party OpenCode row below has an unpaid-account clause). TypeSafe's contract grants it a licence "in perpetuity" to use Customer Data to derive telemetry and to monitor for fraud and abuse; three gateways nonetheless label TypeSafe zero-retention.

DocumentedTypeSafe MCA 4.1 and 4.3, Privacy Policy; OpenRouter, Cloudflare and Vercel pages; checked 1 Oct 2026; route labels rechecked 10 Oct 2026, 05:12 UTC, unchanged since 6 Oct (when Vercel listed a second provider)

If you need zero retention, it has to hold at both layers: the gateway, and TypeSafe as the provider. TypeSafe's docs offer ZDR directly only "for enterprise customers". The MCA licence is a right to process, not a statement that data is kept: MCA 10.3 says TypeSafe has "no obligation to store or retain Customer Data". This does not mean Jev never stores your data. Resellers are excluded because their terms are unknown.

A reading of the text, not legal advice.

Two layers your data passes through

Where a Jev request goes, and whose terms apply at each step

  1. Your applicationSends state and questions. What goes in is up to you and your integration (see payloads).
  2. Gateway layer (if any)OpenRouter, Vercel, Cloudflare or Opper. Its own logging, retention and ZDR terms apply. Going direct to TypeSafe skips this layer.
  3. TypeSafe as providerTypeSafe's MCA, DPA and Privacy Policy apply. U.S. hosting.
    DigitalOcean (Vercel only)Vercel lists it as a second Jev provider and marks it has_zdr: false.
A gateway's statement about itself never stands in for TypeSafe's, and the reverse. Whether DigitalOcean forwards requests to TypeSafe or serves the model itself is not stated. Documented 1 Oct 2026.

Route by term: training, retention and ZDR

Quotes are copied, not interpreted, and each is at most 25 words. Gateway terms and TypeSafe terms sit in separate columns. Where the route is a gateway, the provider column shows what the gateway says about TypeSafe (or another provider). Abbreviations: PP = TypeSafe Privacy Policy (19 Nov 2025); MCA = Master Customer Agreement (23 Sep 2026); DPA = Data Processing Addendum (24 Apr 2026). All three dates were rechecked on 10 Oct 2026, 05:12 UTC and are unchanged; re-read unchanged on 7 Nov 2026, 15:34 UTC (R27-S18). Route pages read 05:26–05:31 UTC.

  • Text supports the safer reading
  • Condition or gap to check
  • Available if you turn it on
  • Not ZDR, or unknown
  • No layer or not stated
RouteTermGateway layer: what the gateway says about itselfProvider layer: TypeSafe (or the provider the gateway names)
TypeSafe direct, standard account
Documented
TrainingNo gatewayNo training without consent
PP: "We (1) will not train or fine tune any artificial intelligence or machine learning models on Input". MCA 4.1: no training on Customer Data "without Customer's prior consent". But MCA 4.3: "TypeSafe may Process Telemetry without restriction, including to improve the Services". Telemetry includes "technical logs, hashes, summary statistics and classifications, metrics, and learnings".
RetentionNo gatewayNo period stated
MCA 4.1(c) grants TypeSafe a licence "in perpetuity" to use Customer Data "(i) to derive and generate Telemetry, (ii) to monitor for fraud and abuse of the Services". MCA 10.3: "no obligation to store or retain Customer Data and may delete Customer Data at any time". DPA Annex §8: "retained for as long as necessary taking into account the purpose of the Processing".
ZDRNo gatewayEnterprise only
Docs: "We also offer zero data retention (ZDR) for enterprise customers." The default for a standard account is not stated.
TypeSafe enterprise
Documented
TrainingNo gatewayAs for a standard account, plus any signed terms (not public).
RetentionNo gatewayNot public
Vercel's ZDR page quotes a clause it attributes to TypeSafe: "TypeSafe shall not retain (a) prompts that are Customer Data for any longer than is necessary to generate Output". This clause is not in TypeSafe's public Terms, MCA, DPA or Privacy Policy (searched 1 Oct).
ZDRNo gatewayOffered
Offered "for enterprise customers"; eligibility, price and terms are not published. Contact changed: the docs legal page now sends ZDR requests to TypeSafe's sales mailbox; its 22 Sep 2026 archive copy named the privacy mailbox. The offer wording is unchanged. The change happened between 22 Sep and 6 Oct (exact date unknown); found by diff on 7 Oct 2026, 05:20 UTC.
OpenRouter
Documented
TrainingNo training
Privacy Policy (31 Aug 2026): "OpenRouter does not use your Inputs or Outputs for model training."
No training
TypeSafe endpoint data policy on OpenRouter: training: false, trainingOpenRouter: false, canPublish: false.
RetentionNot kept by default
"your prompts are not retained unless you specifically opt in to prompt logging."
Not kept
retainsPrompts: false.
ZDRZDR by default
"OpenRouter itself has a ZDR policy". Provider ZDR can be enforced "globally, per model group, per guardrail, or per request". Per request, the zdr parameter "can only be used to ensure ZDR is enabled for a specific request, not to override or disable account-wide or guardrail enforcement" (ZDR docs, read 2 Nov 2026, 10:51 UTC; wording unchanged; R26-S220, R26-S221).
On the ZDR list
Both TypeSafe endpoints are in OpenRouter's ZDR endpoint list: 1,109 endpoints listed on 9 Nov 2026, 11:11 UTC (R29-S29), both TypeSafe endpoints listed; 1,117 on 8 Nov 2026, 05:24 UTC (R28-S46), both TypeSafe endpoints (typesafe/jev-1.14 and typesafe/jev-1.13) listed; 1,119 on 7 Nov 2026, 15:33 UTC (R27-S39), both listed; 1,094 on 2 Nov 2026, 10:59 UTC, with typesafe/jev-1.13-20260917 and typesafe/jev-1.14-20261014 (R26-S39); 941 on 10 Oct 2026. The list changes often: OpenRouter says it is "automatically updated when there are changes to a provider's data policy", and it had 1,095 entries at 10:47 UTC the same morning (R26-S219). typesafe/jev-1.14-20261014 was first seen in the list on 2 Nov 2026; it was not in the 10 Oct read. Earlier: only typesafe/jev-1.13-20260917 (941 endpoints listed on 10 Oct 2026, 05:12 UTC; 951 on 8 Oct; R12-S45). OpenRouter says it "in some cases creates special agreements with providers"; whether one exists with TypeSafe is not stated.
Vercel AI Gateway
two providers: TypeSafe AI and DigitalOcean
Documented
TrainingOn the no-training list
The disallow-prompt-training page (10 Sep 2026) lists "TypeSafe AI ✓".
No training (both providers)
Endpoints API (10 Oct 2026, 05:12 UTC; unchanged since 6 Oct): TypeSafe AI and DigitalOcean both has_no_training: true.
RetentionNot kept
"Vercel AI Gateway has a ZDR policy and does not retain prompts, outputs, or sensitive data."
Not stated per provider
Nothing beyond the ZDR marks below.
ZDREnforceable
On Pro and Enterprise: per request with zeroDataRetention: true (no added cost), or team-wide at $0.10 per 1,000 requests.
TypeSafe AI ✓ DigitalOcean: not ZDR
Vercel's ZDR docs mark "TypeSafe AI ✓", with the quoted clause that is not in TypeSafe's public text. Endpoints API on 10 Oct 2026, 05:12 UTC (unchanged since 6 Oct): typesafe-ai has_zdr: true, digitalocean has_zdr: false (on 1 and 2 Oct it returned only DigitalOcean). The models API's zdr is now "some" (was "none" on 5 Oct) and no_training "all": model-level values across both providers.
Cloudflare Workers AI
Documented
TrainingNo training
Data usage page (21 Apr 2026): Cloudflare does not use your Customer Content "to (1) train any AI models made available on Workers AI".
Third-party terms
Jev is labelled "Third-party": models "may be subject to ... license terms that apply between you and the model provider."
RetentionAI Gateway logs on by default
Content is stored only "if you specifically use a storage service". If you add AI Gateway: "Logs are enabled by default for each gateway" (24 Sep 2026).
Not stated
ZDRNot statedZDR "Yes"
Model page: "Zero data retention Yes".
Opper
Documented
TrainingNo training by default
"No training by default".
No training
"No training on customer data." (route card, "Verified by Opper on 2026-09-18").
RetentionNone on the Gateway plan
"Prompts and outputs stored by Opper: None. Usage metadata only." Control Plane tracing is optional: "1 to 30 days".
Not stated
ZDRZDR rule available
"store no prompts or outputs at Opper and allow only providers that neither train on nor log your content".
Not established
"Zero data retention posture is not established for this route." Region "United States"; "Transfer mechanism unknown".
Lookalike resellers
Reported
All threeUnknown
Eye Security (25 Sep): your prompts pass through the resellers' own servers. Details on official vs reseller sites.
Unknown
OpenCode Console, jev-1.13-free
third-party route; not run by TypeSafe; outside the six routes above; read 2 Nov 2026, 10:47 UTC; re-read 7 Nov 2026, 15:33 UTC, 8 Nov 2026, 05:24 UTC and 9 Nov 2026, 11:11 UTC
Documented
All threeTwo texts, not reconciled
Docs (read 2 Nov 2026; unchanged 7, 8 and 9 Nov 2026): "Our providers follow a zero-retention policy and do not use your data for model training, with the following exceptions:" Jev 1.13 Free is not in the exceptions list, and its free-model entry has no data sentence.
Terms ("Effective date: Nov 8, 2026"; read 9 Nov 2026, 11:11 UTC): "In addition, if you are using the Services through an unpaid account, we may use Content to further develop and improve our Services, except Content obtained or derived from a Connected Service (as defined in our Privacy Policy), which we never use for that purpose." Change: when read on 2, 7 and 8 Nov 2026 the Terms were effective 15 Aug 2026 and the clause ended at "improve our Services." The Terms also said then: "Although we will not retain your Content, we cannot and do not control the retention practices of Third Party Model providers." (8 Nov 2026, 05:24 UTC; that sentence was not re-read on 9 Nov).
OpenCode does not say whether a request to the free model counts as an unpaid account or as Content from a "Connected Service" (the Privacy Policy that defines the term was not read), or which of the two texts controls. (R26-S200, R26-S203, R26-S38; the docs sentence, the exceptions list and the unpaid-account clause with its effective date re-read unchanged on 7 Nov 2026, 15:33 UTC, R27-S37, R27-S38, and on 8 Nov 2026, 05:24 UTC, R28-S37, R28-S38; docs unchanged and Terms re-dated on 9 Nov 2026, 11:11 UTC, R29-S22, R29-S23)
Not stated
Not stated by OpenCode for this route; OpenCode does not say which Jev version it serves. TypeSafe's public pages do not name this route (2 Nov 2026, 10:49 UTC; R26-S215 to R26-S217). Route details: third-party routes.

The OpenCode row is a third-party route outside the six routes read on 1 Oct; it is not counted with them and was not tested by the pool. Netlify is not in this table because its terms were not read term by term. Its AI Gateway docs say "The AI Gateway does not store your prompts or model outputs" (Netlify docs, checked 4 Oct 2026, 05:31 UTC; Documented); TypeSafe's own handling still applies. Sources for each cell are listed at the end of the page.

On Vercel, your request may not reach TypeSafe

Vercel lists two providers for Jev (checked 16 Oct 2026, 05:21 UTC; unchanged since 6 Oct): TypeSafe AI (zero data retention) and DigitalOcean (no zero data retention). Vercel picks a provider by uptime and latency unless you set the provider order. So has_zdr: true on one provider does not tell you where a given request goes: by default Vercel "dynamically chooses the default providers … based on a combination of recent uptime and latency" (provider options, read 6 Oct 2026, 05:24 UTC). So without ZDR enforcement, a Vercel request may be served by DigitalOcean, which Vercel marks as not ZDR. If you need ZDR on Vercel, set zeroDataRetention: true (Pro or Enterprise); Vercel's provider options (order, only) also let you restrict providers (not tested). Whether DigitalOcean forwards requests to TypeSafe or serves the model itself is not stated. On 1 and 2 Oct the endpoints API returned only DigitalOcean. Which Jev version typesafe-ai/jev serves is not stated either (model IDs by route). Documented

Correction: the route matrix previously showed Vercel's zdr "none" as the Vercel data term. That value is a model-level aggregate across both providers, not a statement about TypeSafe.

Which route fits your data?

Open the most sensitive type of data you plan to send; opening one closes the others. Each answer rests on the table above and on the TypeSafe terms below.

Public textAny official route

No route's text permits training on your prompts without consent. Avoid lookalike resellers anyway: their terms are unknown and your prompts pass through their servers.

Personal data (GDPR)The DPA, or ZDR at both layers
  • Direct: sign TypeSafe's DPA (EU Standard Contractual Clauses; the Services are hosted in the U.S.), ask sales for ZDR and get a retention period in writing. None is published.
  • Gateway: enforce ZDR at both the gateway and the provider layer. OpenRouter lists the TypeSafe endpoint as ZDR; on Vercel set zeroDataRetention: true.
  • Opper keeps no prompts on its Gateway plan, but its TypeSafe route is U.S.-based with an "unknown" transfer mechanism.
Health or financial dataNo route documents it

No route found documents HIPAA or a BAA. TypeSafe's public Terms, AUP, MCA, DPA, Privacy Policy and docs contain no HIPAA, BAA or PHI term. Treat this as unsupported until TypeSafe states otherwise in writing.

Secrets in an agent's contextSend less

Prefer integrations that redact or send nothing: the official plugin (no Jev call), jev-claude (regex redaction) or oh-my-claudecode (200-character excerpts, off by default). Avoid guards that send the last 30 messages in full, such as LangChain's AutoModeMiddleware. See payloads.

Data that must stay in the EUNot available at the TypeSafe layer

TypeSafe's Privacy Policy says "The Services are hosted in the United States". Gateway in-region routing (OpenRouter EU, Opper EU) does not change where TypeSafe processes the request. No EU region or residency commitment was found in TypeSafe's text.

No TypeSafe EU region or data-residency option was found in TypeSafe's docs or trust center (checked 5 Oct 2026, 05:14–05:18 UTC; all six subprocessors are listed in the USA). Opper is hosted in the EU, but its Jev route is TypeSafe in the United States ("TypeSafe AI — United States" on its route card). Documented Boundary: TypeSafe docs full text (llms-full.txt, llms.txt), the typesafe.ai homepage and the trust center subprocessors page. Context: a Hacker News user wrote on 30 Sep 2026 "there is only US hosting and I specifically need EU hosting" (HN 49907998). Reported An EU cloud region on Bedrock or Foundry is not a route either: Jev (1.13 and 1.14) is not listed in the Amazon Bedrock model cards at 16 Oct 2026, 05:21 UTC (R17-S34), nor in the Microsoft (Azure AI) Foundry model catalog at 16 Oct 2026, 05:21 UTC (R17-S32, R17-S33); both were also not listed at 12 Oct 2026, 05:15 UTC (Is Jev on Amazon Bedrock or Azure AI Foundry?).

Before you send personal data: 8 checks

CheckWhat to doWhy
Decide which layer must not keep data, then read both the gateway and the provider rows for your route.Route table
On Vercel, set zeroDataRetention: true (Pro or Enterprise) if you need ZDR.Otherwise a request can go to DigitalOcean, marked has_zdr: false
If you route through Cloudflare AI Gateway, turn off logging or payload collection."Logs are enabled by default for each gateway"
Leave prompt logging off (it is opt-in) and enforce ZDR on the request or the account.So a provider policy change cannot reach you
Sign the DPA, ask sales for ZDR and get a retention period in writing.No retention period is published
Snapshot trust.typesafe.ai/subprocessors when you sign, and diarise the 15-day objection window.DPA 3.2: "reasonable advance notice", objection "within 15 days"
Drop names, emails and IDs the decision does not need, and check what your integration sends.Some guards send the full conversation (payloads)
Do not use a lookalike reseller for any non-public data.Their terms are unknown; prompts pass through their servers

Human review, subprocessors and deletion

Documented TypeSafe's PP, MCA, DPA, Terms and docs; gateway pages where read. "Not stated" means not found in those documents.

TermTypeSafe (provider)Gateways
Human review or staff accessNot stated. The nearest text is MCA 4.1(c)(ii), a licence to process data "to monitor for fraud and abuse of the Services". DPA Annex, sensitive-data safeguards: "N/A".Not stated in the gateway pages read
Subprocessors, location and transfersDPA 3.1 authorises subprocessors "as described in https://trust.typesafe.ai/subprocessors". The list was first read on 4 Oct 2026: 6 subprocessors, all in the USA (see below). PP: "The Services are hosted in the United States". DPA 6.1: transfers under the "EU SCCs" or the UK Addendum. DPA 5.2: breach notice "within 72 hours".Opper: TypeSafe route region "United States", transfer mechanism "unknown". OpenRouter: in-region EU and US routing on Business and Enterprise plans; whether Jev is available in-region was not checked
Deletion and opt-outPP: "When you request that we do so, we take measures to delete your personal data". DPA 4.1: TypeSafe forwards data-subject requests to the customer. No opt-out from Telemetry is stated. Training needs the customer's prior consent, so no opt-out is needed for it.OpenRouter: prompt logging is opt-in. Opper: tracing off by default on the Gateway plan. Cloudflare AI Gateway: logging on by default, can be turned off

New on 10 Oct 2026: TypeSafe's Enterprise page says "Zero data retention is available for enterprise customers" and lists the question "Can we run Jev in our own VPC or on-premises?"; its answer is not in the served page and was not read (R12-S58, R12-S110). The same day TypeSafe's status page listed a third monitored service, "api.us-west-2.typesafe.ai: TypeSafe API served from us-west-2"; the pool found no docs text about a regional endpoint (docs llms.txt, 05:13 UTC; R12-S20, R12-S59). Where requests are processed is therefore not documented beyond the subprocessor list below. Documented

Images: what TypeSafe's text says about image data

Since 14 Oct 2026 Jev accepts images, but only with the opt-in TypeSafe-Danger-Zone-Images header. TypeSafe calls images experimental and not yet ready for production. What its pages say about image data, read 16 Oct 2026, 05:21–05:23 UTC: Documented

  • Images page: retention or training of images is not stated on the images page (R17-S06).
  • Models page, "Data handling": "Jev is not trained on customer requests or responses." This applies to requests in general; it does not mention images (R17-S05).
  • TypeSafe's blog post of 14 Oct 2026: "We've added an opt-in to allow you to help find model jaggedness with your queries. We will still not train on your queries" (R17-S09). Where this opt-in is set, and what is kept under it, is not stated on the pages read.
  • Docs legal page: byte-identical to 14 Oct 2026, so no image term was added there (R17-S12).

If your images may show people, documents or other personal data, treat image retention as not stated and ask TypeSafe before sending them. No image was sent and no opt-in was set.

TypeSafe's subprocessors: six listed, two added on 2 Oct 2026

The DPA points to trust.typesafe.ai/subprocessors for the list. The trust center only shows text when its scripts run, so earlier checks (1 Oct) could not read it. On 4 Oct 2026 (05:30 UTC) the pool rendered it with a local headless browser, read-only, with no account and no form submitted; the last recheck, on 11 Oct 2026 (05:18 UTC), found the same six entries and the same single update. Documented

SubprocessorWhat the trust center says it doesLocation
Amazon Web Services"Customer information for live requests is stored and processed on databases, caches and compute nodes within AWS"USA
Modal"Customer AI prompts are processed, but not stored, on compute nodes managed by Modal"USA
Nebius added 2 Oct 2026"Customer AI prompts are processed, but not stored, on compute nodes managed by Nebius"USA
CoreWeave added 2 Oct 2026"Customer AI prompts are processed, but not stored, on compute nodes managed by CoreWeave"USA
SlackListed; purpose not recorded in the pool's notesUSA
Google WorkspaceListed; purpose not recorded in the pool's notesUSA
  • The change: the trust center's only update reads "Nebius and CoreWeave, Published October 2, 2026, Added subprocessors". The DPA (3.2) promises "reasonable advance notice" and an objection window of 15 days; whether customers were notified before 2 Oct was not checked. The addition was a notice on the home page until 10 Oct 2026, when its seven-day shelf life ended; the list itself did not change.
  • "Processed, but not stored" is TypeSafe's own wording about prompts on Modal, Nebius and CoreWeave compute nodes. AWS is described as storing and processing customer information for live requests. Neither statement sets a retention period.
  • SOC 2: the trust center lists a resource named "SOC 2 Type II - 2026" behind "Request access". The report itself was not seen, so the pool states only that the trust center lists it.
  • This does not change any route label above (OpenRouter's ZDR list, Vercel's has_zdr per provider, Cloudflare's "Zero data retention Yes"), which were checked separately.

Compliance terms searched in TypeSafe's text

Searched: typesafe.ai home, Terms, AUP, MCA, DPA, PP, docs legal.md, the models page and llms.txt, 1 Oct 2026. These are negative results within those documents, not proof that no commitment exists elsewhere.

  • Listed, not seenSOC 2The trust center lists "SOC 2 Type II - 2026" behind "Request access" (4 Oct 2026); the report was not seen
  • Not foundHIPAA or BAANo HIPAA, BAA or PHI term in any public document
  • Not foundGDPR as a commitmentThe DPA names the Irish supervisory authority for EEA data subjects and uses EU SCCs
  • Not foundEU region or residencyThe PP says the Services are hosted in the U.S.; none found in the docs or trust center on 5 Oct 2026 (boundary)
  • Not foundISO 27001Opper states ISO/IEC 27001:2022 for itself, not for TypeSafe

What audited integrations send to Jev

Carried from earlier audits with their original check dates; not re-audited this run. Failure behaviour and source links stay on Claude Code and MCP guardrails and products. Documented

IntegrationWhat it sends to JevAudit and check date
Official typesafe@typesafe-ai plugin v0.5.7Nothing: instructions only, it never calls JevCommit 65a39f3, 29 Sep 2026
danna-zhou/jev-mcp hooksThe full shell command, only for commands on its "high-stakes" listCommit 436469a, 29 Sep 2026
brunopivetta88/jev-claude 0.1.0User goal, full tool input with regex secret redaction, last 8 action summaries, working directoryCommit 7d7e876, 29 Sep 2026
jkudish/jev-mcp v0.11.0Only what the agent passes to a tool. v0.12.0 and v0.13.0 were compared with the audited version on 2 Oct 2026: the same content is sent; in 0.13.0 jev_verify puts claim text in state and asks one extra question per claim (version check)29 Sep 2026; checked at 0.13.0 on 2 Oct
LangChain AutoModeMiddleware (langchain-typesafe 0.0.2; read at 0.0.1a3 on 29 Sep) Read at 0.0.2 (wheel, 8 Nov 2026): failure path unchanged; adds an optional classifier= argument on both experimental middlewares. Apart from that argument and its docstrings the middleware code is unchanged and the state-building file is byte-identical, so the content sent is the same (R28-S212, R28-S213; frameworks).The tool call with full arguments, the tool description and the last 30 messages in full29 Sep 2026; checked at 0.0.2 on 8 Nov
oh-my-claudecode v5.5.0Nothing unless OMC_JEV lists points; then per-point text cut to 200 charactersCommit 9fd35ec, 29 Sep 2026
WordPress Jev Comment Triage (soderlind)The default payload includes the comment author's identityProducts ledger, 28 Sep 2026

Row and document text leaves the database when SQL extensions and document pipelines call Jev: pg-jev sends each whole row as JSON, the SQLite extensions send what the SQL passes, pg-redact sends the whole message before it stores it, and DocJev sends page text (source read 8 Oct 2026). Per-project detail: Jev inside SQL and document pipelines. Documented

Third-party privacy claims vs the text

Claim (who, date)What the primary text saysVerdict
"Jev is not trained on customer requests or responses" (jevaiguide.com FAQ, checked 25 Sep) ReportedThe models page and the PP say the same. MCA 4.1 adds "without Customer's prior consent", and MCA 4.3 lets TypeSafe use Telemetry "to improve the Services"Matches but does not address the consent and Telemetry clauses
OpenRouter ZDR for Jev: "Not stated on the Jev page" (jevaiguide.com, 25 Sep) ReportedOn 1 Oct, and again on 2 Oct, the TypeSafe endpoint is in OpenRouter's ZDR endpoint list, and its data policy reads retainsPrompts: falseContradicted as of 1 Oct It may have changed after 25 Sep; the pool has no earlier reading of the list
"Retention is 'as long as necessary' — no number" (jev101.org, "verified 2026-09-28") ReportedDPA Annex §8 and the PPMatches
"Jev is not HIPAA-compliant and does not sign BAAs"; customers must not submit PHI (vendortrustindex.com, "Last verified 2026-09-30") ReportedNo HIPAA, BAA or PHI term in TypeSafe's public documentsNot addressed by public text. Its "SOC 2 Type II current" is Unverified: TypeSafe's trust center lists a SOC 2 Type II resource (4 Oct 2026), but the report was not seen

What was not verified

  • TypeSafe's SOC 2 report: listed on the trust center behind "Request access", not seen. SOC 2 status at the gateway layer.
  • What Slack and Google Workspace process for TypeSafe, and whether customers were notified before Nebius and CoreWeave were added.
  • Whether DigitalOcean on Vercel forwards requests to TypeSafe or serves Jev itself, why Vercel's endpoints API returned only DigitalOcean on 1 and 2 Oct, and which provider served any given request (no request was sent).
  • Whether OpenRouter's ZDR listing of the TypeSafe endpoint rests on a special agreement, and whether the clause Vercel quotes comes from a contract that standard accounts also get.
  • Human review or staff access at any layer; a TypeSafe retention period; a Telemetry opt-out.
  • How TypeSafe retains or uses images, and where the "model jaggedness" opt-in is set and what it keeps (not stated on the pages read, 16 Oct 2026).
  • Netlify AI Gateway's data terms, beyond one docs sentence (4 Oct): whether TypeSafe retains prompts sent through Netlify, Netlify's region and any ZDR label.
  • No account was opened and no request was sent on any route. This is a reading of public text only.

Sources and check times (1 Oct 2026, UTC)

  • TypeSafe: Privacy Policy, MCA, DPA, Terms and AUP: quoted from the pool's captures of 30 Sep; "Last updated" dates rechecked 05:16. Docs legal page and models page (05:16). Trust portal (05:26, unreadable on 1 Oct).
  • 4 Oct 2026: TypeSafe trust center subprocessors and updates, rendered with a local headless browser at 05:30:18–05:30:35 UTC (R7-S80); Netlify AI Gateway docs (05:31:22 UTC, R7-S82).
  • 5 Oct 2026: route data labels (OpenRouter ZDR list, Vercel endpoints, Cloudflare model page, Opper route card) and TypeSafe legal "Last updated" dates rechecked 05:13:31–05:15:03 UTC, unchanged (R8-S29, R8-S33, R8-S40–R8-S44, R8-S48, R8-S49); trust center subprocessors rendered again at 05:14:25 UTC, unchanged (R8-S45); TypeSafe docs full text searched for "data residency", "region", "eu" and "europe" at 05:17:54 UTC (R8-S110); HN item 49907998 (05:21:28 UTC, R8-S121).
  • 6 Oct 2026: route data labels (OpenRouter ZDR list, Vercel models and endpoints APIs, Cloudflare model page, Opper route card) and TypeSafe legal "Last updated" dates rechecked 05:15:34–05:15:35 UTC (R9-S28, R9-S29, R9-S33, R9-S40–R9-S44, R9-S48, R9-S49); only Vercel changed (second provider, TypeSafe AI, has_zdr: true). Vercel provider options 05:24:28 UTC (R9-S112); Vercel Jev model page 05:24:29 UTC (R9-S113). Trust center subprocessors rendered again at 05:17:16 UTC, unchanged (R9-S45).
  • 7 Oct 2026: route data labels (OpenRouter ZDR list, Vercel models and endpoints APIs, Cloudflare model page, Opper route card) and TypeSafe legal "Last updated" dates rechecked 05:19:15 UTC, unchanged (R10-S45, R10-S28, R10-S46, R10-S29, R10-S33, R10-S37). Docs legal page compared with the Internet Archive copy of 22 Sep 2026, 15:56 UTC at 05:20:20 UTC: two changes only, the ZDR contact mailbox (privacy mailbox to sales mailbox) and a footer line (R10-S38). Trust center subprocessors rendered at 05:20:29 UTC, unchanged: 6 entries (R10-S39).
  • 8 Oct 2026: route data labels (OpenRouter ZDR list, Vercel models and endpoints APIs, Cloudflare model page, Opper route card) and TypeSafe legal "Last updated" dates rechecked 05:14:04–05:14:06 UTC, unchanged (R11-S45, R11-S28, R11-S46, R11-S29, R11-S33, R11-S37). Docs legal page: 1,168 bytes at 05:14:05 UTC, the same size as on 6 and 7 Oct, so no diff was needed (R11-S38). Trust center subprocessors rendered at 05:15:17 UTC, unchanged: 6 entries; the only update is still "Nebius and CoreWeave, Published October 2, 2026" (R11-S39).
  • 10 Oct 2026: route data labels (OpenRouter ZDR list, Vercel models and endpoints APIs, Cloudflare model page, Opper route card) and TypeSafe legal "Last updated" dates rechecked 05:12:20–05:12:21 UTC, unchanged (R12-S45, R12-S28, R12-S46, R12-S29, R12-S33, R12-S37); the OpenRouter ZDR list now has 941 endpoints and still lists typesafe/jev-1.13-20260917. Docs legal page: 1,168 bytes, byte-identical to 8 Oct (R12-S38). Enterprise page (R12-S58) and status page (R12-S20) read 05:12–05:13 UTC.
  • 10 Oct 2026: trust center subprocessors and updates rendered 05:12:31–05:12:41 UTC, unchanged: 6 entries; the only update is still "Nebius and CoreWeave, Published October 2, 2026" (R12-S39).
  • 11 Oct 2026: trust center subprocessors and updates rendered 05:18:15–05:18:49 UTC, unchanged: 6 entries; the only update is still "Nebius and CoreWeave, Published October 2, 2026" (R13-S11).
  • 16 Oct 2026: models page "Data handling" (05:21 UTC, R17-S05); images page, searched for retention, training, deletion and storage terms (05:22 UTC, R17-S06); TypeSafe's blog post of 14 Oct 2026 (05:23 UTC, R17-S09); docs legal page, byte-identical to 14 Oct (R17-S12).
  • 2 Nov 2026: OpenRouter ZDR endpoint list 10:47:49 UTC (1,095 entries; R26-S219) and 10:59:40 UTC (1,094 entries; both TypeSafe endpoints; R26-S39); OpenRouter ZDR docs and provider selection docs 10:51:32–10:51:33 UTC (R26-S220, R26-S221). OpenCode: Console models docs (redirects to opencode.ai/v2/docs/console/models/; 10:47:47 UTC, R26-S200; quote re-read 10:58:23 UTC, R26-S38), Terms of Use and Privacy Policy (10:47:48 UTC, R26-S203, R26-S204).
  • 9 Nov 2026: OpenCode Console models docs (11:11:41 UTC: jev-1.13-free still listed "Free", the zero-retention sentence and its exceptions list unchanged, R29-S22) and Terms of Use (11:11:41 UTC: "Effective date: Nov 8, 2026"; the unpaid-account clause now adds an exception for Content from a "Connected Service", R29-S23). OpenRouter ZDR endpoint list 11:11:42 UTC (1,109 entries; both TypeSafe endpoints; R29-S29). TypeSafe docs legal page byte-identical to 8 Nov (11:07 UTC, R29-S15).
  • 8 Nov 2026: OpenCode Console models docs (05:24:49 UTC, HTTP 200: jev-1.13-free still listed "Free", the zero-retention sentence and its exceptions list unchanged, R28-S37) and Terms of Use (05:24:49 UTC: unpaid-account clause present, effective date Aug 15, 2026, R28-S38). OpenRouter ZDR endpoint list 05:24:51 UTC (1,117 entries; both TypeSafe endpoints; R28-S46). TypeSafe docs legal page byte-identical to 7 Nov (05:17 UTC, R28-S15). langchain-typesafe 0.0.1a3 and 0.0.2 wheels (05:19 UTC, R28-S212, R28-S213).
  • 7 Nov 2026: OpenCode Console models docs (the old address opencode.ai/docs/zen now redirects to opencode.ai/docs/console/models/; 15:33:26 UTC, R27-S37) and Terms of Use (effective 15 Aug 2026; 15:33:26 UTC, R27-S38): the quoted docs sentence, the exceptions list and the unpaid-account clause unchanged. OpenRouter ZDR endpoint list 15:33:26 UTC (1,119 entries; both TypeSafe endpoints; R27-S39). TypeSafe docs legal page byte-identical to 2 Nov (R27-S15); legal "Last updated" dates unchanged: Privacy Policy Nov 19, 2025; MCA Sep 23, 2026; DPA Apr 24, 2026; Terms Sep 19, 2026 (15:34:32 UTC, R27-S18).
  • OpenRouter: Jev 1.13 page and data policy, ZDR docs, privacy and logging, Privacy Policy (05:26); ZDR endpoint list (05:27).
  • Vercel: Jev model page and ZDR docs (05:26); disallow-prompt-training page (05:28); endpoints API (05:30); models API (05:16).
  • Cloudflare: Workers AI data usage, Jev model page, AI Gateway logging (05:26).
  • Opper: TypeSafe route card (05:26); security docs, ZDR and retention rules (05:29).
  • Third parties: Eye Security (05:16); jevaiguide.com, jev101.org, vendortrustindex.com (05:26).

Search published pools, pages, reports, and evidence.