OpenRouter by OpenRouter

# Fix list: OpenRouter

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/openrouter, the October 2026 research run, assessed 1 October 2026. Grade B, 68.8 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 OpenRouter: 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, 55 out of 100, up to 9 more on the total

Why it scored 55: Status page at status.openrouter.ai, but it renders only in a browser, and its feed and JSON paths answered 403 to our reader on both days (10 of 20, and 5 for the incident line). The limits page gives 20 requests a minute on free models, 50 a day below $10 of lifetime purchases and 1,000 a day above, no platform cap on paid models, and a key endpoint that reports what's left (15). The errors page says 429, 503 and some 402 responses may carry `Retry-After`, tells clients to honour it, and says the official SDKs already do (15). The pricing page lists 'Contractual SLAs' for Enterprise without publishing terms, which we count as no published SLA (0). The chat completions API is GA (10). Model fallbacks through a `models` list soften an upstream outage, which this checklist doesn't score.

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, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No machine payment protocol found in the docs index. Credits can be bought in USDC through Coinbase, but calls draw on a prepaid balance (0). Per-token prices published per model without a login (20). 25 or more free models with no card, per the listing (20). Browser sign-up for the first key (0). Management API keys and OAuth PKCE mint keys in code, but only after a person has an account.

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, 60 out of 100, up to 7 more on the total

Why it scored 60: Model reading. Bearer keys with per-key credit limits, Management API keys for creating and rotating keys in code, and OAuth PKCE for user-delegated keys. No permission scopes (25 of 30). OpenRouter doesn't store or use prompts unless you opt in for a 1% discount, but the routing reference sets `data_collection` to 'allow' by default, which admits 'providers which store user data non-transiently and may train on it'. An account privacy setting can switch that off, and the docs don't say what a new account starts with (5 of 20). Prompts not stored by default and a per-request `zdr` filter (15). Request metadata kept for reporting, per-call logs not confirmed (10 of 15). security.txt valid per the listing's provenance check. No certification or 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.

## 4. Agent ergonomics, 85 out of 100, up to 2.4 more on the total

Why it scored 85: Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calling documented, behaviour depends on the routed model (15 of 20). Structured outputs depend on the upstream model (10 of 15). Prompt caching documented, discount set by each provider (10 of 15). Routes to models with 1M-token context, a judgement call since a router has no default model (15). Batch API, usually half price per the listing (10). Official SDKs in TypeScript, Python and Go (10). Errors and debugging page (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.

## 5. Transparency & trust, 74 out of 100, up to 2.3 more on the total

Made of editorial 55, provenance 92.

Why it scored 74: Closed service with clear terms, SDKs Apache-2.0 (15). Data collection page and privacy policy agree that content isn't stored unless you opt in, but training defaults for upstream providers sit on other pages we didn't read (15 of 30). Changelog notes deprecations with dates, no policy (10 of 20). Each provider's data policy is shown per endpoint per the listing, and EU or US in-region routing is a Business feature. No subprocessor list checked (15 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: openrouter.ai, registered 2023-04-17 (3 years) (7 of 15)

## 6. Schema & documentation, 90 out of 100, up to 1.6 more on the total

Why it scored 90: Public OpenAPI document at openrouter.ai/docs/openapi/openapi.yaml (25). llms.txt with Markdown twins (10). Reference not read in full this run (15 of 20). Structured outputs documented, enforcement depends on the upstream model (10 of 15). Errors and debugging page and examples throughout (15). Dated API changelog (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.

## 7. Maintenance & community, 84 out of 100, up to 1.4 more on the total

Why it scored 84: Model reading. The TypeScript, Python and Go SDKs were all tagged on 1 October 2026, v1.4.18, v1.3.19 and v0.9.19 (30). No stated notice policy for API changes, but the 25 July Responses GA entry says removal of the beta aliases 'will be announced here with a sunset date before it ships', and the 28 July rename of `judge_model` kept a deprecated alias (6 of 12). No OpenRouter-side shutdowns found in the last 90 days, model churn sits with upstream providers (8 of 8). Dated changelog, newest entry 19 August, nothing in September, support not checked (10 of 15). SDK issue replies not sampled (5 of 10). Official SDKs in three languages, generated from the OpenAPI document with Speakeasy and released many times a day, 100 to 150 tags each since 4 July (15). Each SDK repository runs PR validation and publish workflows (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.

## 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.

- unchecked: status page incident history, since the page renders only in a browser and its feed and JSON paths answered 403
- What a new account's privacy setting starts at. The routing reference defaults `data_collection` to 'allow', and the account setting's default isn't stated
- unchecked: the crypto fee, the $0.80 minimum, USDC refund rules and credit expiry, which come from the listing because the terms and the pricing FAQ render only in a browser
- The API changelog has no entry after 19 August 2026 while the SDKs are regenerated daily, so spec changes may land without a changelog line

## Weaknesses

- No machine payment. USDC top-ups go to a prepaid balance
- `data_collection` defaults to 'allow', which admits providers that may store and train on prompts
- Mid-stream failures arrive inside a 200 response, and upstream providers may charge for prompt processing on a failed call
- No published SLA, and the status page gave us no readable history
- API changelog silent since 19 August 2026

## 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.

- Set `provider.data_collection: "deny"` or `provider.zdr: true` when the prompt holds anything private
- Pass a `models` list so a failed provider falls through to the next one
- Honour `Retry-After` on 429 and 503, and check the stream body for errors even on a 200
- Set `max_price` so a routed request can't land on an expensive provider
- Free models allow 50 requests a day until $10 of credit has been bought. Check `GET /api/v1/key` for what's left

## What the review panel asked for

- a written API deprecation policy
- changelog lines for spec changes
- Refund unused USDC credit

## 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.