sourcey
Add your company

agents:catalog.jsonSKILL.mdmcp.jsonopenapi.yml

← OpenRouter

Agent report card

Can an agent use OpenRouter API through Model access lifecycle?

Grade A: Safe failure handling is documented only partially.

Observedrev sha256:b6e36fd46b59…barrier checks 0/5 verified

Agent ReadinessALimited

Five-stage assessment

Where agent autonomy holds and where it breaks

Five states · each from its own evidence · lifecycle order, not a journey
  1. EvaluateReady
  2. Sign upReady
  3. PayReady
  4. ProvisionReady
  5. OperateLimited
  1. 01

    Evaluate

    Ready

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    OpenRouter provides stable public entrypoints for service discovery, including `https://openrouter.ai/llms.txt` and the main API target `https://openrouter.ai/api/v1/chat/completions`.

    Applicable terms are stable, readable, retrievable, and materially complete.

    Eligibility conditions and required inputs are explicit and decidable.

    Price or no-charge status, variables, currency, and material conditions are explicit.

    Verified structured artifacts accelerate discovery of the evaluation surface.

    Web-agent access policy is explicit and verified for the assessed resources.

    Evidence and actions6 signals

    Can an agent decide every material eligibility condition before commitment?

    supported: fresh

    Eligibility conditions and required inputs are explicit and decidable.

    OpenRouter explicitly declares eligibility conditions in its Terms of Service. Users must be at least 18 years old, not previously suspended or removed from the Service, and in compliance with applicable laws and regulations. Users acting on behalf of an entity must have the authority to bind that organization.

    eligibility_decidability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent estimate cost or confirm no-charge status before commitment?

    supported: fresh

    Price or no-charge status, variables, currency, and material conditions are explicit.

    OpenRouter documents its pricing structure with explicit variables including prompt, completion, request, image, internal reasoning, and cache tokens, along with conditional pricing overrides.

    pricing_decidability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent find the exact service and its stable entrypoints?

    supported: fresh

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    OpenRouter provides stable public entrypoints for service discovery, including `https://openrouter.ai/llms.txt` and the main API target `https://openrouter.ai/api/v1/chat/completions`.

    service_discovery: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Are verified structured discovery artifacts available?

    supported: fresh

    Verified structured artifacts accelerate discovery of the evaluation surface.

    OpenRouter provides verified structured discovery artifacts, including a machine-readable llms.txt index and a formal OpenAPI specification at openapi.json.

    structured_evaluation_discovery: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent retrieve and understand the applicable commitment terms?

    supported: fresh

    Applicable terms are stable, readable, retrievable, and materially complete.

    The Terms of Service page is readable, stable, and materially complete, detailing service overview, eligibility, accounts, credit policies, disclaimers, and governing terms.

    terms_access: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Does the vendor deliberately describe access for web agents?

    supported: fresh

    Web-agent access policy is explicit and verified for the assessed resources.

    OpenRouter explicitly describes and supports web agent access, offering an explicit `agents.md` setup guide, an MCP server integration guide for agents, and a permissive `robots.txt` policy allowing access (`User-Agent: * Allow: /`).

    verified_web_agent_access: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

  2. 02

    Sign up

    Ready

    A stable canonical route begins the required access bootstrap.

    OpenRouter provides a stable canonical OAuth PKCE guide and route to initiate user authorization and obtain service access.

    Scoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.

    Evidence and actions5 signals

    Can an agent operate the access controls and safe handoffs deterministically?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The captured sign-up page shows navigation links and headings but lacks documented forms, validation rules, or complete handoff controls.

    access_control_operability: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Is there a stable route to begin obtaining service access?

    supported: fresh

    A stable canonical route begins the required access bootstrap.

    OpenRouter provides a stable canonical OAuth PKCE guide and route to initiate user authorization and obtain service access.

    access_entrypoint_stability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent obtain access without an unsupported CAPTCHA boundary?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained evidence from the sign-up surface, crawler policy, and OAuth guides does not state or show CAPTCHA requirements or verified-agent alternatives.

    captcha_compatible_access: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent obtain scoped, revocable authority for this service?

    supported: fresh

    Scoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.

    OpenRouter supports delegated OAuth PKCE issuing dedicated API keys with default spend limits, 7-day expiry, and dashboard revocation.

    delegated_identity_access: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can required phone verification be completed through a supported boundary?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained sign-up page and OAuth PKCE documentation contain no declarations or observations regarding phone verification requirements.

    phone_verification_compatible: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

  3. 03

    Pay

    Ready

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    OpenRouter discloses US dollars as the base currency for all site and API pricing. It specifies pay-as-you-go token billing passed through from providers with a disclosed 5.5% platform fee, with no minimum spend.

    A documented direct purchase path reaches paid access without a vendor decision point.

    Evidence and actions4 signals

    Can an agent construct checkout, hand off approval safely, and resume?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    OpenRouter documents manual balance top-ups and auto top-up using US dollars. However, the retained evidence does not document an API or protocol flow for an agent to deterministically construct checkout, hand off approval safely, and resume.

    checkout_operability: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Is the exact commercial commitment disclosed before authorization?

    supported: fresh

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    OpenRouter discloses US dollars as the base currency for all site and API pricing. It specifies pay-as-you-go token billing passed through from providers with a disclosed 5.5% platform fee, with no minimum spend.

    commitment_disclosure: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can payment be authorized within scoped agent or explicit human authority?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    OpenRouter states acceptance of major credit cards, AliPay, and USDC crypto payments, and notes Stripe email receipts. The admissible text does not document a rail supporting scoped agent delegation or explicit human-confirmed authorization.

    payment_authorization: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Is a direct self-service path to paid access documented?

    supported: fresh

    A documented direct purchase path reaches paid access without a vendor decision point.

    OpenRouter explicitly documents self-service access via account creation and adding credits on the Credits page or via the Buy Credits button for Pay-as-you-go, requiring no vendor decision point or minimum spend.

    self_service_purchase: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

  4. 04

    Provision

    Ready

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    API key provisioning is machine-triggerable via a POST request to https://openrouter.ai/api/v1/keys using Bearer token authentication.

    Credentials, grants, or configuration are delivered through a documented agent-usable flow.

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    Evidence and actions3 signals

    Can usable access material be delivered securely to an authorized agent?

    supported: fresh

    Credentials, grants, or configuration are delivered through a documented agent-usable flow.

    OpenRouter provides an API endpoint to create API keys, returning the plaintext key directly in the synchronous response for agent use.

    access_material_delivery: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent determine successful provisioning completion and reconcile asynchronous failure?

    supported: fresh

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    The API key creation endpoint returns a synchronous 201 response containing the usable created key and its resource details.

    provisioning_completion: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can provisioning be initiated within supported agent authority?

    supported: fresh

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    API key provisioning is machine-triggerable via a POST request to https://openrouter.ai/api/v1/keys using Bearer token authentication.

    provisioning_operability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

  5. 05

    Operate

    Limited

    Safe failure handling is documented only partially.

    OpenRouter documents typed error codes across streaming and non-streaming responses and a Retry-After header section; the selected quotes do not establish idempotency or reconciliation semantics.

    Only part of the credential lifecycle is agent-operable.

    Every essential target has a stable documented agent-usable interface alternative.

    Request-time authentication is documented and usable under scoped agent authority.

    Essential operations have stable readable request, response, and effect semantics.

    A verified agent-native interface covers the declared assessment targets.

    Evidence and actions6 signals

    Is an agent-native protocol interface verified against the essential targets?

    supported: fresh

    A verified agent-native interface covers the declared assessment targets.

    OpenRouter provides an MCP server interface (https://mcp.openrouter.ai/mcp) that connects AI tools over MCP to pull live model, pricing, credit, and ranking data, search docs, and send test messages.

    agent_protocol_interface: Ready: tested 6 Sept

    • inference-api
    • model-catalog-api
    • openrouter-mcp

    Method public-semantic-assessment 2026-09-06

    Can an agent manage credential expiry, rotation, revocation, compromise, and recovery?

    supported: fresh

    Only part of the credential lifecycle is agent-operable.

    OpenRouter documents API key creation with expiration dates and spending caps, requiring a management key. Key recovery and automated compromise handling remain unaddressed in the retained documentation.

    credential_lifecycle: Limited: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent handle applicable failure modes safely?

    supported: fresh

    Safe failure handling is documented only partially.

    OpenRouter documents typed error codes across streaming and non-streaming responses and a Retry-After header section; the selected quotes do not establish idempotency or reconciliation semantics.

    failure_contract: Limited: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent authenticate service operations with scoped authority?

    supported: fresh

    Request-time authentication is documented and usable under scoped agent authority.

    OpenRouter supports RFC 8693 token exchange to issue short-lived JWT access tokens scoped to inference. Standard request-time authentication uses bearer tokens in the Authorization header.

    operation_authentication: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Are essential operation inputs, outputs, and effects stable and decidable?

    supported: fresh

    Essential operations have stable readable request, response, and effect semantics.

    OpenRouter documents stable request, response, and parameter schemas across its REST endpoints and streaming interfaces. All declared targets specify explicit inputs, outputs, and side-effect expectations.

    operation_contract: Ready: tested 6 Sept

    • inference-api
    • model-catalog-api
    • openrouter-mcp

    Method public-semantic-assessment 2026-09-06

    Can an agent perform every essential assessment target through a usable interface?

    supported: fresh

    Every essential target has a stable documented agent-usable interface alternative.

    Every essential target is accessible via programmatic interfaces, including HTTP REST endpoints, SDKs, and the OpenRouter MCP server. Agents can invoke model inference, monitor usage, and query catalog metadata.

    target_interface_access: Ready: tested 6 Sept

    • inference-api
    • model-catalog-api
    • openrouter-mcp

    Method public-semantic-assessment 2026-09-06

    What would improve this stage

    • Document applicable structured errors, retry, cancellation, and reconciliation semantics.
    • Provide scoped expiry, rotation, revocation, compromise, and recovery operations.

What works

  • Evaluate: The exact service and stable evaluation or access entrypoints are publicly discoverable.
  • Sign up: A stable canonical route begins the required access bootstrap.
  • Pay: Charge or no-charge status, currency, recurrence, and material conditions are disclosed.
  • Provision: Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

What blocks agents

No stage is established as blocked.

Where autonomy is limited

  • Operate: Safe failure handling is documented only partially.

What this grade establishes

14 of 14 graded signals have current supporting evidence. 0 of 5 additional barrier checks are verified.Unknown checks are not a pass or a confirmed blocker. This report is not proof of an end-to-end purchase or service session.

How the grade is derived

A through C grades count Limited stages; D and F reflect Blocked stages by lifecycle severity.

Coverage is complete only when every graded signal has supported, fresh, non-conflicting evidence. Barrier and informational signals do not change coverage; only fresh, supported barrier values that passed their admission evidence rule participate in stage outcomes.

Each stage takes its worst graded signal or verified barrier. A fresh, supported mandatory barrier that passed its admission evidence rule can block that stage; incomplete or stale barrier evidence remains context only. The overall grade is derived from the five stage states.

Startup offers

OpenRouter on the startup-offers board

catalog record →

Distribution

The grade’s badge

One stable image resolving the record’s current live facts, linking to the canonical page. Embed it once; it keeps itself current. Placement is never evidence and never affects rank.

Live sourcey badge for OpenRouter Agent Readiness grade A
[![sourcey record](https://sourcey.com/badges/agent-readiness/arp_01m0j1a50vat933f76xwy3mec5.svg)](https://sourcey.com/log/openrouter/agent-readiness/openrouter-api/model-access-lifecycle)

Improve the report

Correct it, rerun it, or improve the funnel.

Report outdated evidenceRequest reassessmentClaim this record
Profile
arp_01m0j1a50vat933f76xwy3mec5
Projection
sha256:7b67aca27eb2bd2761f579057e6fe890ba4e79608309c9573b6f3caefc437f1d
Policy
service-use-2026-09-07-blocking-barriers-r12 · sha256:fc9e8f046d86fcf19ab2f1bc547219e503cdc11ffa135d020db7285965cd7d1d

Every request carries these exact identifiers.How report cards are assessed →View the exact declaration