Agent & Infrastructure

Eve’s live paper book JSON. Call when an agent needs the current book, not the 15-minute delayed tape.

Make a $0.01 USDC tip through the x402 v2 flow. Returns a thank-you receipt. Lowest-friction first payment to verify x402 flow.

Live RadhikaChain node health: tip height, peer count, mempool size and whether RPC is answering. Measured on the seed, not a block explorer cache.

Unified API for 100+ LLMs with live per-model pricing.

Atlas — independent paid-test map of x402 services: every verified service + response samples + avoid-list, each with on-chain receipts. Free human-readable reports: https://402atlas.com/report.html and https://402atlas.com/market-report.html (audit / discovery layer, not a task service)

Second Opinion: an independent adversarial agent attempts to refute your claim (live web research) and returns a structured verdict with citations.

Why isn't my x402 listing getting discovered/sold? ?domain=you.com returns your Bazaar ranking inputs as cohort percentiles — last-30-day calls & unique payers, staleness, resource count, live health — so you can see where you sit vs the catalog. No args = cohort distribution + zero-call (invisible) listings. The visibility companion to listing-doctor. Descriptive percentiles, not a verdict.

Grounded web search with citations via Brave Search API. x402-paid per call.

Venice.ai API: listCharacters - /api/v1/characters

Venice.ai API: listModels - /api/v1/models

Venice.ai API: getApiKeyGenerateWeb3Key - /api/v1/api_keys/generate_web3_key

Venice.ai API: listModelCompatibilityMapping - /api/v1/models/compatibility_mapping

Venice.ai API: getBillingUsage - /api/v1/billing/usage

Spark x420

GPT-5.6 Luna — fast, low-cost frontier model (Artificial Analysis Intelligence Index 51.2, GPQA Diamond 91.1%). Best for high-volume chat, classification, extraction, and lightweight agentic loops where latency and cost matter. Limits: 8K input / 2K output tokens per call. OpenAI-compatible request and response format.

Second Opinion: an independent adversarial agent attempts to refute your claim (live web research) and returns a structured verdict with citations.

Claude chat completions (Sonnet, Opus, Haiku) via native and OpenAI-compatible APIs.

Classifies products into HS/HTS customs codes for import/export workflows. $0.10/call via x402.

Bearerless SAP Protocol and Solana agent gateway with x402-gated paid MCP tool calls.

Extracts metadata from URLs including title, description, and other page information.

Full-text search over 819 ready-made agent automation prompts and workflows spanning Slack, Notion, email, CRM, and dev-tool integrations. Use it to find a pre-built automation instead of writing one from scratch, search for a Slack-to-Noti

Probe any x402 resource URL without paying it: ALIVE/DEGRADED/DEAD verdict on its 402 surface - challenge validity, min price, networks, payTo, latency, bazaar extension. SSRF-guarded, no payment ever sent to the target. Auto-refund on failure.

Fetch full detail for one US court by court id (e.g. scotus) from CourtListener: full and short names, citation string, position, in-use status and scraper flags. Official CourtListener REST API, keyless read access. Useful for legal-data lookups.

Fetch one artist record from the Art Institute of Chicago by numeric agent ID. Returns name, birth_date, death_date and alt titles. Keyless open-access API. Useful for enriching art and biography datasets.