ChatGPT Instant Checkout / OpenAI ACP

openai.com · Agent-Commerce Infrastructure modeIntegrated

Last probed 2026-08-16 17:31 UTC · Verified (Documented)

ChatGPT Instant Checkout / OpenAI ACPIn-chat shopping that hands off to the merchant's own checkout to complete purchase.

60 / 100Interrupt Score(range 4873 · 14 properties unassessed)How much automated use this service interrupts — the badge-driving metric. Unassessed properties are provisionally scored at 50%; evidence-graded successes at 25%.
Custody / RiskNot applicable
ConfidenceVerified (Documented)

Verdict: An agent can activate on its own. Discover, operate, and manage aren't assessed yet.

  1. DiscoverNot assessed
  2. ActivateEasy
  3. OperateNot assessed
  4. ManageNot assessed

Capability parity

Each stage answers one question about what an agent can do unattended. Stages are ordered by the credential-gateway dependency: Activate issues the keys that unlock Operate and Manage.

Discover

Can an agent find and read it, no account?

Not assessed
  • Be found by a retrieval agentNot assessed
  • Read what it does and how to use itNot assessed
  • Read pricing & limits without loginNot assessed

Activate

Can an agent sign up and walk away with the keys it needs?

Easy
  • Create an account self-serveNot assessed
  • Obtain an API / MCP access credentialNot assessed
  • Obtain a management / admin keyNot assessed
  • Accept the terms without a bot-banEasy

    No bot-prohibition signal found.

    Evidence
    Path tried
    ToS / policy scan
    Where it stalled
    completed
    Evidence tier
    Tier 0 (passive scan)
    Verification
    Evidence-only — graded from passive signal, not live-verified.

Operate

Can an agent do the service's actual jobs — call, transact, pay?

Not assessed
  • Call the primary service over MCP / APINot assessed
  • Complete a transaction / checkoutNot applicable

    Integrated tool — the API call is the transaction, no separate checkout.

  • Pay via an agent rail (x402 / ACP / AP2)Not assessed

Manage

Can an agent administer the account and provision resources?

Not assessed
  • Provision / scale / tear down a serviceNot assessed
  • Change account details / set budget / rotate keysNot assessed
  • View usage & billingNot assessed
  • Cancel / export / delete (offboard)Not assessed

Interrupt tier: Moderate-Interrupt — derived from 1 finding; interrupt score 60 / 100 — the badge-driving metric. (range 47.872.8 · 14 unassessed)

Every tool starts at 100. Each interrupt found subtracts a penalty of base weight × timing × hardness × evidence — the multiplier values below come from the same rubric tables the score is computed with. New snapshots also provisionally subtract 50% of the full worst-case tax for each unassessed property and 25% for evidence-graded successes not live-verified by Tier 2.

Property coverage

A check only counts as clean when a probe tier capable of detecting that interrupt actually ran and found nothing. Not tested ≠ clean.

PropertyStageStateEvidenceRequired
Mandatory redirect to vendor’s own siteoperate failedActive finding — itemized in the penalty matrix below. Tier 1 assesses this property.no
CAPTCHA / bot-challengeactivate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 0 assesses this property.no
Email OTP verificationactivate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 1 assesses this property.no
SMS / phone OTP verificationactivate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 1 assesses this property.no
Mandatory phone verification callactivate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
Mailed physical code (postal)activate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
“Contact sales” wall (no self-serve path)activate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
Manual approval queueactivate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
ToS clause banning automated/bot accessdiscover unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 0 assesses this property.no
SSO-only signup, no API-key issuanceactivate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 1 assesses this property.no
Rate-limit-triggered manual reviewmanage unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
One-time account / payment-method provisioningmanage unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
Identity / KYC verificationactivate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
Crypto wallet / key-custody setupoperate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.no
No Machine Interfaceoperate unassessedNo probe tier that can detect this has run yet — unknown, not clean. Tier 1 assesses this property.yes
Interrupt foundBase weight× Timing× Hardness× Evidence= Penalty
Starting score100
Mandatory redirect to vendor’s own siteEvery transactionEvery purchase hands off to the merchant's own checkout page to complete (publicly documented product behavior, post-rollback Instant Checkout / Agentic Commerce Protocol model).4×8every transaction×1soft×0.8Documented−27.2
Total penalty27.2
Full unknown tax 253.2 — capped at 25 (point score uses 50% of the capped value)253.2
Raw score = 100 − 27.2 = 72.8
Point score = 72.8 − 50% × 25 − 25% × 0 = 60.3 → 60
60

What would make this Easy

One concrete change per blocker found. These are the diffs between this listing's current parity and an unattended agent path.

How we scored this

Machine-readability checks not yet recorded

Four check groups, equal weight: machine interfaces, browsing efficiency, element discoverability, and discovery/agent access. Each check carries an evidence grade (proven / plausible / emerging) — an honesty label that never weights the score. What these mean →

No per-check breakdown recorded for this listing.

Evidence & history

Last probed 2026-08-16 17:31 UTC. The raw JSON is the archival record.

This is the first assessment on record.

DateScoreBadgeRubric version
2026-08-16 17:31 UTC60Moderate-Interrupt (current)[email protected]

Alternatives in Agent-Commerce Infrastructure

Other Agent-Commerce Infrastructure tools in the same mode (integrated), ranked by Overall LLM-Friendliness (the mean of Interrupt Score and Machine-Readability) — comparable to this listing because they share its usage mode.

Embed this rating

Copy this snippet to display your Interrupt Index seal on your site — the seal image and link stay in sync with your latest probe automatically. Pick the variant that matches your site’s theme.

Light (default)

<a href="https://interruptindex.com/tools/chatgpt-instant-checkout-openai-acp"><img src="https://interruptindex.com/badge/chatgpt-instant-checkout-openai-acp.svg" alt="ChatGPT Instant Checkout / OpenAI ACP — Interrupt Index agent-readiness rating" height="64"></a>

Dark

<a href="https://interruptindex.com/tools/chatgpt-instant-checkout-openai-acp"><img src="https://interruptindex.com/badge/chatgpt-instant-checkout-openai-acp.svg?theme=dark" alt="ChatGPT Instant Checkout / OpenAI ACP — Interrupt Index agent-readiness rating" height="64"></a>