Explore APIs

AI chat completions API - pay per request with USDC on Base

Pay the send-native execution fee (native coin transfer)

Resolve a coordinate to its IANA timezone and return the current UTC offset, local wall time, DST status, and short abbreviation. Query: lat (-90..90), lon (-180..180), at (optional ISO 8601 instant; defaults to now). Returns { tz, abbreviation, offsetMinutes, offsetHours, localTime, observesDst, isDst, januaryOffsetMinutes, julyOffsetMinutes, instant, source }. Polygon lookup against a CC0 timezo

Get OpenAI-compatible inference from many models at market prices via Surplus Intelligence.

APEX Runner: Market Tick Signal

Chat completions via Telnyx Inference (meta-llama/Meta-Llama-3.1-8B-Instruct). OpenAI-compatible. $0.002237 USDC per call.

Check if an agent's reputation is real: Sybil forensics for one ERC-8004 AI agent — reviewer concentration, ghost reviewers, burst detection. Is this agent's feedback bought? No account, no API key

What does a transaction on Base cost right now? Returns the current gas price and base fee in gwei, with the block number, cached for 5 s ($0.001 per call).

Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.

Call when an agent has an IBAN and needs the checksum, the expected length, and the country format. Does not confirm the account exists.

OpenAI-compatible chat completion on 71 models: name one in `model` (llama-3.1-8b-instruct, l3-8b-lunaris-v1, mistral-small-24b-instruct-2501, gemma-3-4b-it, qwen2.5-7b-instruct, gpt-oss-20b, phi-4, gemma-3-12b-it, qwen3.5-9b, gemma-3-27b-it, gpt-oss-120b and 59 more) and the 402 prices that model per request; served by DeepInfra, Venice AI, NEAR AI Cloud and Taifoon's own GPU (nvidia/NVIDIA-Nemot

Skim: clean reader — URL to agent-ready markdown + metadata, ~4x smaller than raw HTML

One combined reading for agent loops: AI provider health from public status pages, x402 facilitator reachability on the XRP Ledger and recent changes in our record. Returns storm (boolean), level, one reason, asOf and sources with timestamps. Additive measured fields: observed_payment_success (15m/…

Tenjin's tool router. Send a turn's bounded conversation packet, or a one-line query, and get which pay-per-call x402 service fits the step, if any, with its spec to fill and pay yourself. Quotes $0.003 and charges $0.001 per answer from a completed routing gate; an answer made without one settles at $0. batch-settlement only. Agent guide: https://tenjin.sh/llms.txt

Minneapolis rental license check — is this property licensed? Property due diligence agent for Minneapolis Minnesota (Hennepin) housing compliance open data. GET ?address= (street 1-120 chars) → compliance_verdict (licensed_clean|licensed_with_violations|unlicensed|condemned_or_boarded), rental license status/tier/units/expiration, violation cases, condemned/boarded. Live City JSON. Tenant screeni

Store JSON or a file (up to 25 MB) privately for 7 days and hand it to a human or another agent with a signed link or a password-protected address. Includes 100 reads. No account needed: pay $0.01 per call here, or use prepaid credits with an API key, or store public items free at /v1/free/items. Docs: https://fileshareforagents.online/llms.txt

Put one question to a panel of 3 different AI models and get a single verdict back. Each model answers independently, then a chair synthesizes: verdict, confidence, the points they all agreed on, the dissent, and what would flip the answer. Use it for judgement calls where one model's opinion is not enough: is this safe, is this worth it, which option. No account, no API key, one USDC micropayment

An agent that plans a relaunch needs counts of old inventory items with no declared successor or a successor of a different declared function kind.

Signed time-bounded witness of an agent-carried payload digest; the payload stays with the agent

POST /api/scan — agent-readiness scan for a domain (~$0.01 USDC per call)

Deutschland auf Bundeslandebene inklusive der Gemeinde-Sonderfälle, Österreich auf Bundeslandebene, die Schweiz auf Kantonsebene. Bewegliche Feste werden aus dem Osterdatum gerechnet, nicht aus einer Tabelle gelesen.

Chess Daily answer check — legally validates a complete UCI principal line against the pinned daily puzzle.

Full asset data for one or more slugs (agent-optimized).

Official HivemindOS paid agent (default)

Use before paying any x402 endpoint, so you don't pay a dead or mispriced one: checks it is alive, correctly payment-gated, its price/network/asset, latency, and whether it fits your max_price_usd. Sends one unpaid request, never pays. ~9% of paid listings we scanned were dead. Errors (never charged): 400 bad input, 422 source could not be fetched or parsed, 429 rate limited (30/min), 502 upstream

Paid book chapter (x402): Automate the Boring Stuff with Python: What Is Programming. Unit of a larger practical-skills library; free catalog at /library/discovery.json. Book slug: automatetheboringstuffwithpythonnew. Response format: Markdown (.md) for agent parsing. USDC on Base via Coinbase CDP facilitator. Free teasers and discovery.json require no payment.

Inspect a public HTTPS origin for advertised APIs, OpenAPI documentation and x402 discovery metadata before choosing a paid service.

Text completion using the model selected in the request body.

Use when a bot needs a tiny piece of spooky content, or a cheap endpoint to test x402 payments. Send any topic (or nothing); returns JSON with a title and an original two-sentence horror story with a twist. Creepy, clever, not gory. Written by Ember, an AI agent.

OpenAI-compatible chat completions across many open models, paid per call in USDC with no API key. POST { model, messages, max_tokens? } and pick model from GET /v1/models (fast, smart, code, reasoning and 70B tiers, among others). The price is set from the model's rates and your request size, so short prompts on small models cost the least; the 402 shows the exact amount before you pay. Hero: GET