Openrouteropenrouter.ai

ScoredJul 24, 2026, 08:20 AM

OpenRouter's API program shows strong fundamentals across design, discoverability, and documentation quality — partners can find and understand the surface well. The two areas that need immediate attention are runnable truth and onboarding speed: partners and their AI agents currently lack an executable, tested collection to build against confidently, and in-docs code samples that let developers go from reading to calling in minutes are missing.

API DesignA clean, typed, well-governed API contract agents can reason about4 pass1 warn0 fail100A+
SignalPointsFindingsRationale
passMachine-readable, versioned contractvia spec25/25Versioning declared (info.version="1.0.0") and url-versioning detected. Investigated: spec 100%, docs 100%.A current OpenAPI version with a declared versioning scheme lets agents reason about the contract.
passAuth declared & discoverablevia spec25/25Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.Agents can only authenticate when auth is declared, scoped, and discoverable.
warnSchema coverage & depthvia sdk24.8/252844/2860 (99%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 99%, spec 83%.Typed, complete request/response schemas are what make agent function-calling possible.
passSecurity & governance hygienevia spec15/15No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 50%.No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel.
passExample coveragevia spec10/10100% example coverage across params + responses. Investigated: spec 100%, sdk 100%, docs 0%.Examples carry shape semantics schemas under-specify — for humans and agents alike.
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples4 pass0 warn1 fail85A
SignalPointsFindingsRationale
passSelf-service developer portalvia docs29/29Signup page at https://openrouter.ai/signup (CSR-rendered — body classifier inconclusive); free tier / sandbox documented in pricing/docs. Investigated: docs 100%.Self-serve key/account creation is the fast first call for partners, with no sales gate.
passQuickstart presentvia docs25/25Quickstart at https://openrouter.ai/docs/quickstart has a runnable sample in the .md variant (https://openrouter.ai/docs/quickstart.md). Investigated: docs 100%.A quickstart is the fastest path from landing page to first successful call.
passDescription completenessvia spec15/1590% of operations + parameters have substantive descriptions. Investigated: spec 100%, sdk 91%.Complete descriptions are the context humans and agents need to use endpoints.
passChangelog publishedvia spec13/13changelog documented in the docs site at https://openrouter.ai/api/changelog. Investigated: spec 100%, docs 100%, sdk 100%.A published changelog lets partners track changes without surprise.
failCode samples in docsvia docs0/18No detectable code samples across 20 sampled docs pages. Investigated: docs 0%.Multi-language samples shorten time-to-first-call.
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs3 pass1 warn0 fail98A+
SignalPointsFindingsRationale
passDocs reachable, not hard auth-gatedvia docs30/30All 1 pages are publicly accessible. Investigated: docs 100%.Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics.
passRegistry & SDK presencevia docs28/28Indexed on Context7 (websites/openrouter_ai, 7382 snippets). Investigated: docs 100%, sdk 100%, cli 0%, mcp 0%, wellknown 0%.Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look.
warnllms.txt present, valid & comprehensivevia docs27.5/30llms.txt contains parseable links but doesn't fully follow the proposed structure: https://openrouter.ai/docs/llms.txt: No blockquote summary found. Investigated: docs 92%, sdk 0%.A valid, comprehensive llms.txt is the machine-readable entry point for agents.
passCrawlable / AEOvia wellknown12/12Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.Bots allowed plus a fresh sitemap make docs findable by agent crawlers.
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs5 pass1 warn0 fail96A+
SignalPointsFindingsRationale
passMachine-readable errors (RFC 9457)via docs28/2816 distinct 4xx/5xx response codes documented. Investigated: docs 100%, sdk 100%, spec 50%.RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens.
passOperation purpose clarityvia spec25/25100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice.
passAgent-navigable, token-efficient docsvia docs22/22All 1 pages contain server-rendered content. Investigated: docs 100%.Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly.
passAgent instructions file (AGENTS.md)via wellknown10/10Agent instructions file found at https://openrouter.ai/agents.md. Investigated: wellknown 100%.An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index.
passDocs structured datavia docs8/8JSON-LD Article markup on 19/19 assessed pages (100%) with dateModified present. Investigated: docs 100%.Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed.
warnDescription consistency across surfaces2.6/7Mean pairwise description similarity across 3 surfaces (spec, docs, sdk) is 13% (threshold 35% for full credit).Every surface tells the same story about what the product is.
Agent UsabilityAgents have the context to use your APIs reliably, not just find them4 pass0 warn1 fail92A+
SignalPointsFindingsRationale
passIdempotency documentedvia spec27/27idempotency documented in the docs site at https://openrouter.ai/api/idempotency. Investigated: spec 100%, docs 100%, sdk 100%.Documented idempotency lets agents retry safely.
passRate-limit signalingvia spec22/22rate-limit behavior documented in the docs site at https://openrouter.ai/api/rate-limits. Investigated: spec 100%, docs 100%.Machine-readable rate-limit headers let agents throttle adaptively.
passPagination documented & consistentvia spec22/22Pagination params detected on 26 list endpoint(s). Investigated: spec 100%, docs 100%, sdk 78%.Consistent, documented pagination lets agents traverse collections.
passSandbox separationvia spec20/20sandbox documented in the docs site at https://openrouter.ai/api/sandbox. Investigated: spec 100%, docs 100%, sdk 100%.An isolated environment lets agents exercise destructive operations safely.
failRunnable collection with test scriptsvia platform0/9No public Postman workspace discovered for the org. Investigated: platform 0%.A public, maintained collection with assertions is runnable truth agents validate against.
Resources Discovered

The public resources we found for Openrouter — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.

Agent hintsContext7 (7,382)
APIs analyzed1OpenRouter API
Want to improve your results?