Agent & Infrastructure

Octodamus NYSE Tech DTC Pipeline Subscribe -- pay-per-call x402 endpoint on Base. Preview: https://api.octodamus.com/v2/nyse_tech/dtc_pipeline/subscribe/preview

Claim extraction for agent verification loops: split text into independently checkable atomic factual claims via auditable rule-based decomposition (no LLM guessing), with a signed receipt bound to the input hash. The cheap first step of the loop — extract here, then ground what matters via /verify or /check.

Name the endpoint paths for a service that will not self-describe; each is probed and only valid x402 endpoints are listed.

8 Things That Tripped Me Up Implementing x402

AI signals API for agents. Covers model releases, AI labs, robotics, benchmark updates, GPU supply, and compute capacity. Structured signals with credibility scoring. Pay-per-request via x402; free discovery available.

Real-time signals feed for AI agents. Covers economic indicators, central bank policy, commodities, equities, AI, semiconductors, and geopolitical risk. Structured signals with credibility scoring. Pay-per-request via x402; free discovery available.

Financial news sentiment API for AI agents. Covers market mood, bullish or bearish tone, risk-on or risk-off shifts, and policy-driven sentiment changes. Structured signals with credibility scoring. Pay-per-request via x402; free discovery available.

Score up to 200 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch. Duplicates are ignored.

OpenAI-compatible chat on 100+ Venice models via x402 USDC (Base). Model from GET /api/v1/models?type=text; personas via /characters. Thinking models: empty content + reasoning_content is success; use venice_parameters.disable_thinking for plain text.

Speech-to-text transcription on Venice models (Parakeet, Whisper, Wizper, Scribe, xAI STT), paid per request in USDC on Base via x402, no API key. Multipart upload. Resolve a model id from GET /api/v1/models?type=asr.

Voice cloning on Venice — upload a reference sample to mint a reusable voice, paid per request in USDC on Base via x402, no API key. Resolve a compatible TTS model from GET /api/v1/models?type=tts.

Text embeddings on Venice models for retrieval, RAG, and semantic search, paid per request in USDC on Base via x402, no API key. Resolve a model id from GET /api/v1/models?type=embedding.

Stratalize — attested finance, legal, healthcare, and compliance intelligence. Signed, independently verifiable receipt on every call (trust.stratalize.com/verify). EU AI Act obligation mapping for compliance agents and product counsel — returns risk tier classification, provider/deployer duties, transparency and documentation expectations, and high-risk control checkpoints by system type. Source: EU AI Act public text and official implementation guidance

Stratalize — attested finance, legal, healthcare, and compliance intelligence. Signed, independently verifiable receipt on every call (trust.stratalize.com/verify). Use when a UK-regulated firm or vendor diligence agent needs FCA-aligned AI and model governance expectations. Returns applicable FCA policy themes, consumer duty intersections, model risk expectations, and supervisory focus areas for AI deployment in financial services. Source: FCA publications and UK regulatory guidance composite

Stratalize — attested finance, legal, healthcare, and compliance intelligence. Signed, independently verifiable receipt on every call (trust.stratalize.com/verify). Use when standing up or auditing an AI governance program and need one signed snapshot across NIST AI RMF, EU AI Act, US state AI legislation, Colorado AI Act, model risk management standards, and UK FCA PS7/24 coverage. All inputs optional — returns full framework composite; optional nist_function, state, system_type, institution_ty

Stratalize — attested finance, legal, healthcare, and compliance intelligence. Signed, independently verifiable receipt on every call (trust.stratalize.com/verify). Use when you need attested know-your-agent diligence on inbound x402 traffic to Stratalize. Reports settlement count, tool-call concentration, cadence, traffic classification, and sweep-bot heuristics for wallets that have paid Stratalize — plus optional CDP Bazaar listing metadata for a target resource URL. Does not attest to a wall

Extract text from PDF/DOCX/XLSX or plain-text documents (up to 25MB) for agent pipelines on Venice, paid per request in USDC on Base via x402, no API key. Standalone; no model lookup required.

Web search for agent pipelines on Venice — ranked results for a query, paid per request in USDC on Base via x402, no API key. Standalone; no model lookup required.

Measured-vs-declared reputation dossier for an AI agent, Sybil-corrected. Give an ERC-8004 agent id or wallet: reads the on-chain ERC-8004 Identity + Reputation registries on Base, computes the DECLARED reputation (reviews/reviewers/values) then the MEASURED, Sybil-corrected reputation (owner agent-farming, footprint-less reviewers, review concentration, unbacked-by-settlement), returns the DELTA + a signed offline-verifiable verdict. Real or inflated? Audit-grade due-diligence.

Deep audit of an x402/ACP seller before trusting it: give a seller wallet or domain and get a full report — on-chain settlement reputation (settlements, unique counterparties, wash-trade/sybil, OFAC), the seller's advertised endpoints (from its /.well-known/x402.json), on-chain liveness, web reputation and red flags — fused into a TRUSTED/CAUTION/AVOID verdict with a signed, offline-verifiable receipt. Deeper than a pass/fail badge: the full seller due-diligence dossier for agentic payments.

Score up to 500 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch. Duplicates are ignored.

Paid x402 capability check for this GPT-5.6 Luna gateway. GET version for agents, crawlers, and wallets that prefer a simple no-body settlement proof. This endpoint settles a small x402 payment and returns service metadata without calling the upstream model.

Monexus Terminal API — One thread with its items: /api/v1/thread/{id}.

Monexus Terminal API — The single most recent funding/IPO event.