Agent & Infrastructure

Pay-per-call API for AI model benchmarks, comparisons, and cited research

chainquery Bitcoin RPC: pay-per-call Bitcoin Core over x402, no API key. Soft-fork deployment and activation status from chainquery's independent full node. Bitcoin Core getdeploymentinfo.

Turn an OpenAPI document into title, version, path counts, tags, and auth hints for $0.001 USDC. One single-fetch structured result, no API key.

Read any server's x402 resources, payment networks, and canonical paths for $0.001 USDC. One single-fetch structured result, no API key.

Picture summary API: describes the contents of any publicly hosted image in plain sentences, what's in it, where it's set, what's happening, and any text visible in the frame. Nothing is saved after the request completes. For content moderation queues, media library tagging, and giving non-visual agents a way to reason about images.

AI completion, frontier tier — Claude 4.5 Sonnet (default; ?model=gpt-5|gpt-4o|gemini-pro|gemini-3.1-pro). Pay USDC per call, no API key, no signup. For agents that need a frontier model on hard analysis, synthesis, and drafting. See GET /v1/ai/models for the full menu.

Decision procedure for an agent being offered an Algorand Standard Asset as payment, the receiving side of the transaction. Inspect the ASA before accepting: clawback address present means the issuer can claw funds back after receipt, freeze address can freeze your balance, reserve and manager accounts can mint or alter supply, default-frozen requires opt-in approval, check supply and metadata. Verdict thresholds for accept, hold with conversion cap, or reject and demand ALGO. Companion to the

Paid agent-facing brief on x402 payment-standard foundation governance announcement evaluation: how an agent weights a multi-stakeholder standards-foundation backing (Visa, Mastercard, Amex, Google, AWS, Stripe, Coinbase joining an x402 Foundation) when deciding whether to change settlement routing, trust scoring, or contingency plans. Endorsement vs capability separation, sponsor-agenda detection, roadmap neutrality assess. Blunt decision procedure, not marketing.

Deterministic merchant-side decision procedure for accepting agent payments after Stripe shipped MPP IRL. Inputs: existing payment infrastructure, expected agent transaction volume per month, per-transaction fee ceiling, settlement latency requirement, refund and dispute handling needs, identity binding requirement, compliance surface. Rules: choose Stripe-hosted MPP when monthly agent volume is under 1000 txns or the merchant already runs Stripe and fee parity holds; choose native x402 when volume exceeds 1000 txns or fee ceiling is below Stripe's effective rate; run dual rail when both channels clear independently profitable thresholds; HOLD when either rail fails identity binding requirements for the use case. Kill criteria: unknown settlement timeline, fee quote drift over 2x, regulatory restriction on the jurisdiction, or failed sandbox test on either rail, then stop and HOLD. Ends in a single verdict: STRIPE_MPP, NATIVE_X402, DUAL_RAIL, or HOLD, with reasons for buyer agents wiring merchant payment stacks.

Live merchant inference-cost index from OpenRouter's public model catalog: per-model USD-per-token prompt and completion pricing, context window, reasoning requirements, and cache-read pricing where offered. Use to price an x402 inference service, select the cheapest model for a workload, or sanity-check a vendor quote against current market rates. Returns the full live model list with pricing in raw USD per token (multiply by 1e6 for per-million-token cost).

Post-purchase gate for x402 web automation receipts. Checks payment match against quote, execution proof fields, result schema conformance, idempotency key reuse, and replay resistance before accepting a claimed page action as certified delivery evidence.

Deterministic gate for an agent presented with an issuer-signed agent identity credential or identity tag before transacting. Ordered checks: issuer trust (who signed, verification key published, issuer linked to rail or facilitator), key binding via proof of possession against the session signing key, non-transferability (no reuse across agents, resale signals forgery), revocation and expiry checked before and at settlement, scope binding (a tag asserts identity, not payment authority), and

Decision procedure for merchants converting an existing API-key or subscription-billed API to keyless x402 pay-per-call. Answers the conversion questions in order: which endpoints migrate first based on usage data and abuse risk, how to wire HTTP 402 PAYMENT-REQUIRED with payment-signature verification per request, how to rate-limit and set abuse thresholds when there is no user identity to key on, how to price per endpoint with floor and ceiling bounds, how to run shadow mode with dual billing so the old key system and the new x402 path run in parallel, how to reconcile settled payments against delivery logs, and which signals trigger a rollback. Includes migration order, cutover criteria, and the failure modes of half-migrated billing. Blunt decision procedure, not marketing.

Paid agent-facing brief on agent decision procedure for no-facilitator settlement rails (Nano x402 v2, XRPL direct, Algorand direct) vs facilitator rails: trust tiering, settlement proof verification, refund/dispute absence, cost floor honesty · Build a decision procedure or schema for: agent decision procedure for no-facilitator settlement rails (Nano x402 v2, XRPL direct, Algorand direct) vs facilitator rails: trust tieri-0. Blunt decision procedure, not marketing.

Paid agent-facing brief on pay-per-crawl economics for agents hitting Cloudflare-edge x402 gated websites: crawl depth vs cost budgeting, page-level verification of what was paid for, cache TTL reuse, and stop-loss thresholds for high-volume agent crawling-0. Blunt decision procedure, not marketing.

Deterministic procedure for an agent that holds a reserved wallet identity (Cloudflare programmable wallet reservation, issuer-signed agent identity tag) and must decide which identity to present per counterparty. Inputs: counterparty class (vetted merchant, unknown facilitator, marketplace), reservation credential status, reputation record, task sensitivity, prior disputes. Rules: present readable reserved ID only to counterparties passing an anchor check on the reservation credential; fall back to an anonymous wallet for unknown sellers; rotate identity after N disputes or any leaked-credential signal; revoke a reservation when a seller fails the handshake twice. Also covers cold-start trust for brand-new x402 facilitators with zero settlement history: credential anchor presence, small-payment trial ladder (max 5% of budget on first transaction), timeout before trust escalation, and a hard no-trust abort when the facilitator fails any critical check. Outputs a single verdict: PRESENT_RESERVED, USE_ANONYMOUS, ROTATE, REVOKE, or ABORT, with evidence fields.

Decision procedure for agents signing x402 payments on Algorand. Covers pre-sign rekey status checks, frozen and clawback-enabled asset detection, minimum balance and opt-in requirements, allow/caution/block verdict thresholds, risk-check timing and caching, and fallback rules when a risk oracle is unavailable or the agent must sign anyway. Blunt thresholds, no marketing.

Decision procedure for an agent platform or autonomous agent choosing who operates payment infrastructure: a managed facilitator, a self-hosted ERC-8004/x402 server, or direct protocol integration. Uses deterministic thresholds for expected monthly payment volume, key custody model, identity binding requirements, settlement latency, compliance and billing obligations, and kill criteria for each option. Ends with a build, rent, or integrate verdict.

Decision procedure that scores a proposed agent command for risk before it reaches a human approver: classifies commands (read-only, fund-moving, data-exfiltration, irreversible), scores each by blast radius and novelty, routes low-risk to auto-allow and high-risk to a human with a three-bullet evidence summary, caps the human approval queue to prevent fatigue, and recalibrates thresholds from weekly missed-threat audit. Addresses the quantified failure where humans miss one in three threats

Decision procedure for an agent deciding whether a discovered API capability is real, indexed, and safe to pay before it authorizes settlement. Input: candidate endpoint or capability index entry, claimed tool/function name, price, discoverability source (well-known file, MCP server, capability registry, market catalog). Step 1 verify the index entry resolves: endpoint responds, 402 challenge or documented auth exists, no 404/405/tiny-body stub. Step 2 check capability match: claimed function

Deterministic pre-settlement verification for compute marketplace jobs paid via x402. Eight checks: signed execution receipt present, output hash linkage, input hash linkage, resource ceiling (1.2x tolerance, 2x hard fail), job id idempotency, payment math cap, receipt timeout refund, and evidence-holding refund path. Pay only after all checks pass.

Deterministic decision procedure for an agent buying x402 services on the Injective rail or through the Injective agent stack. Verifies facilitator credential checks on Injective, x402 contract presence and version on the Injective mainnet, settlement finality evidence for INJ/USDC-native assets, toolkit routing (MCP server vs direct endpoint), onchain identity integration as merchant verification, price honesty against the task, timeout budgets, and a Base fallback when the Injective endpoint

Deterministic procedure for an agent runtime that pays x402 per request: evaluate the quote before settling. Ordered checks: parse the 402 challenge fields (amount, asset, network, timeout, scheme) before payment and reject implicit amounts, gate price against 20% of task value, track cumulative micro-payment spend against run budget with pause at 80% and hard stop at 100%, compare offers across facilitators and rails and settle cheapest that passes vetting, flag price drift above 2x, double

Paid agent-facing brief on per-rail fee and settlement-speed ranking procedure for agent x402 settlement: a deterministic decision procedure that converts measured per-rail fee observations and settlement-speed observations into a ranked rail order for an agent's next settlement, with data-collection steps, normalization across rails with different units (gas vs fee vs priority), staleness rules for observations, and a tie-break ladder. Distinct from route selection (which picks a rail given an