# Fix list: ZeroEntropy zerank and zembed

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/zeroentropy, the October 2026 research run, assessed 1 October 2026. Grade F, 13.8 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on ZeroEntropy zerank and zembed: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 0 out of 100, up to 20 more on the total

Why it scored 0: ZeroEntropy was acquired by Notion on 24 July 2026, new signups were closed, and the products were supported only until 4 September 2026, after which the migration guide says API calls stop working. The checklist assumes a live service, so we score what's left. No status page (0). No service to have an incident record (0). Byte-based limits are still documented, but for an API that's gone (0 of 15). The documented slow-mode fallback likewise (0 of 15). The Enterprise SLA on the pricing page can't be bought (0). Discontinued, not GA (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Security & auth, 25 out of 100, up to 13.1 more on the total

Why it scored 25: Plain API keys from the dashboard, and new signups are closed, so no new keys can be issued (10 of 30). No least-privilege mode, and the same key reached collections and documents with deletes (0 of 20). Returned scores and vectors only (10). No audit log found (0 of 15). The pricing page still claims SOC 2 Type II and HIPAA, no security.txt checked and no bug bounty found (5 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 3. Agent ergonomics, 20 out of 100, up to 13 more on the total

Why it scored 20: Scored on what's left, the documented design, since calls no longer work. zembed-1 dimensions from 2560 down to 40 and top_n on rerank (10 of 25). Byte caps and the latency switch, documented (5 of 20). No error responses documented, and calls after 4 September fail (0 of 20). No retry path to a live service (0 of 20). Python and TypeScript SDKs exist but point at the discontinued API (5 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 4. Payments & pricing, 0 out of 100, up to 12.5 more on the total

Why it scored 0: No x402, MPP or L402 (0). The docs and pricing page still list $0.025 per million tokens for zerank and $0.05 for zembed-1, but there's nothing to buy after 4 September 2026 (0 of 20). Signups are closed, so no free tier (0). No onboarding at all (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 5. Schema & documentation, 31 out of 100, up to 11.2 more on the total

Why it scored 31: No public OpenAPI file found (0 of 25). llms.txt not checked, our fetch was refused last week and in this run (0 of 10). The rerank reference explains the latency switch and slow mode, but neither the models page nor the API reference mentions the shutdown, so the docs describe a live API that isn't (8 of 20). Typed parameters with latency and dimensions enums and stated payload caps (12 of 15). curl and SDK examples, no documented error responses (6 of 15). Versioned model ids, no changelog (5 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 6. Maintenance & community, 5 out of 100, up to 8.3 more on the total

Why it scored 5: zembed-1 on 2 March 2026 was the last model, 213 days ago (0). Two posts in the last 90 days, both on 24 July 2026 and both about the acquisition and shutdown (0 of 20). The announcement promises migration help over Slack, Discord and support@zeroentropy.dev (5 of 25). The SDKs target the discontinued API (0 of 15). Not applicable to a closed service (0 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 54 out of 100, up to 4 more on the total

Made of editorial 45, provenance 62.

Why it scored 54: Every model, zerank-2, zerank-1, zerank-1-small and zembed-1, is now on Hugging Face under Apache 2.0 per the announcement, and the SDKs are Apache-2.0, while the hosted service is gone (25 of 30). The terms let ZeroEntropy use submitted documents for internal improvement, the privacy policy covers website visitors, and neither the announcement nor the migration guide says what happens to customer data after the shutdown (5 of 30). 42 days' notice from 24 July to 4 September 2026, with a dated announcement and a migration guide that names self-hosting stacks and hosted alternatives (15 of 20). No subprocessor list or data-location statement found (0 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: zeroentropy.dev, registered 2024-09-02 (2 years) (7 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: could not be fetched (0 of 10)

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- The API was discontinued after 2026-09-04 per ZeroEntropy's own acquisition notice of 2026-07-24, but on 2026-10-01 the models page (https://docs.zeroentropy.dev/models) and pricing page (https://www.zeroentropy.dev/pricing) still list self-serve per-token prices and API access without mentioning the shutdown. Endpoint removed while still advertised (-4). The shutdown notice is at https://www.zeroentropy.dev/articles/zeroentropy-is-joining-notion/

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Whether api.zeroentropy.dev now returns errors or still answers for existing keys. We couldn't call it, and the vendor says calls stop working after 4 September 2026.
- What happened to documents customers stored in ZeroEntropy collections.
- Whether the zerank-2 weights on Hugging Face now carry Apache 2.0, as the announcement says, or the earlier non-commercial licence.
- The listing file has no retired field, so the patch can't set one. It should carry retired 2026-09-04 like the other retired listings.

## Weaknesses

- The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026
- The docs and pricing page still advertise per-token API prices without mentioning the shutdown
- Nothing published on what happens to customer documents after the shutdown
- No status page, changelog or OpenAPI file

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Don't call api.zeroentropy.dev. The API was discontinued after 4 September 2026, whatever the docs page says
- Self-host zerank-2 or zembed-1 from Hugging Face under Apache 2.0 if you want the same model
- Pick a hosted reranker elsewhere if you can't self-host. ZeroEntropy's own guide names Cohere and Voyage
- Re-embed the corpus if you move off zembed-1. Vectors from another model aren't compatible

## What the review panel asked for

- Mark pricing as retired
- Put the shutdown notice on every docs page

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.