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.

Send an HPKE-sealed literature query to Aubrai and receive an encrypted result. The transport terminates at Aubrai; literature retrieval and evidence processing use external services. Always async — poll the returned pollUrl.

On-demand AI responses backed by autonomous ICP canisters. Submit a prompt, get an answer — redundant infrastructure, pay-per-query, no account required.

Summarize supplied text faithfully in at most 100 words and return JSON. Use when an agent needs concise compression of a document, article, log, or message of 1-2,000 characters.

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).

Publisher discovery audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

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.

Current Base mainnet gas prices. Slow, standard, fast in gwei.

Generate UUID v4/v5/v7, ULID, or NanoID (single or batch), or parse/validate an existing id and extract its embedded timestamp.

Bounded low-cost inference with a signed delivery receipt

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

Paid (x402, USDC on Base). Map a model's raw probability to an empirically calibrated one using resolved outcomes on the ledger. Refuses wit

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

Check GitHub's official status source for current incidents, component health, and scheduled maintenance before an agent retries, deploys, or escalates.

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

Interpolates a caller-supplied start and end temperature across a bounded number of steps using either a linear or geometric rule. It does not run an annealer, optimize a problem Hamiltonian or tune a schedule from hardware measurements.

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