Celeris-1 Decision

# Fix list: Celeris-1 Decision

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/celeris-1-decision, the October 2026 research run, assessed 9 October 2026. Grade D, 49.3 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 Celeris-1 Decision: 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, 40 out of 100, up to 12 more on the total

Why it scored 40: Component status and incident history earn 20. Only one day of history is possible for this model, so incident evidence earns 5, not a clean 90-day award. Documented 429 and backoff earn 15. Numeric request rates were not found (0). Enterprise SLA marketing gives no public commitment (0). Early-access terms prevent a general-availability award (0). The August Celeris-1 outage is a different model.

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. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: Public per-token prices earn 20. No machine-payment protocol found (0). Card-funded activation and credit purchases prevent a card-free trial award (0). Browser signup and activation prevent autonomous onboarding credit (0). Total 20.

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.

## 3. Security & auth, 45 out of 100, up to 9.6 more on the total

Why it scored 45: Revocable bearer keys earn 20. Workspace isolation earns 10 of 20 for least privilege, but no scoped inference permissions or per-key limits were found. No decision-specific prompt-injection mitigation found (0). Usage records and trace IDs earn 15. SOC 2 appears in enterprise marketing without a reviewed report or trust evidence, so no security-programme award (0). Total 45.

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.

## 4. Schema & documentation, 60 out of 100, up to 6.5 more on the total

Why it scored 60: No public machine-readable decision contract found (0). Markdown and llms.txt earn 10. Purpose and limitations earn 20, typed question variants and explicit limits 15, and examples and errors 15. Versioned paths alone do not establish a public changelog (0). Total 60.

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.

## 5. Maintenance & community, 40 out of 100, up to 5.3 more on the total

Why it scored 40: The dated 8 October decision-model launch earns 30. No decision-model deprecation notice period or release history found (0). A support email is published but public response evidence was not found (0). Documented current client compatibility earns 10 of 15, not an award for Celeris-owned SDK maintenance. No owned decision package CI found (0). Total 40.

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.

## 6. Transparency & trust, 53 out of 100, up to 4.1 more on the total

Made of editorial 45, provenance 61.

Why it scored 53: Closed model with service terms earns 15. Privacy and security statements explain processing and 90-day usage records, but not prompt retention or a training exclusion, earning 15 of 30. No dated deprecation policy found (0). Named subprocessors and regional-routing disclosure earn 15 of 20; a decision-specific residency guarantee was not found. Total 45.

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: celeris.ai, no registry record we could read (0 of 15)
- Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10)
- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Agent ergonomics, 80 out of 100, up to 3.3 more on the total

Why it scored 80: Compact probability answers earn 25. Multiple questions, bounded options and image controls earn 15 of 20; no exact token window or decision output-budget control was found. Actionable errors earn 20. Retry guidance earns 10 of 20 because duplicate inference can be billed and no idempotency contract was found. Simple required fields and documented compatible Python clients earn 10 of 15; no Celeris-owned decision SDKs in two languages found. Total 80.

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.

## 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.

- We did not run authenticated inference or reproduce the vendor benchmark.
- What are the exact decision-model context window and sustained request-rate limits?
- What are prompt and response retention periods, training defaults and available data-residency commitments?
- Launch copy says keys are live immediately, but activation documentation still describes a capacity queue.
- The well-known security.txt and docs OpenAPI JSON addresses returned 404; no alternative public machine-readable decision contract was found.
- No independent security certification evidence or public SLA terms were reviewed.

## Weaknesses

- Early-access terms and capacity-dependent workspace activation
- Prepaid credit expires after 30 days, with a $5 minimum card purchase
- No numeric request-rate guarantee or decision-model context window found
- No explicit API training exclusion or prompt-retention period found in the reviewed policies
- Closed weights and no fine-tuning in this release

## 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.

- Use the decision model path and matching model field. This model has no chat, Responses or models endpoint.
- Use at most 512 questions per request, or 64 with explanations. Both endpoints reject streaming.
- Preserve x_celeris in a custom Jev SDK response model when reading explanations. The default response type drops it.
- Retry 429 with Retry-After and backoff. Stop on 402 until workspace credit is replenished.
- Read usage.input_tokens for cost, including images and request overhead. Track credit expiry separately from token consumption.

## 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.