Every agent-payable API.

Live health of every supported chain in one call: chain id, block height and how stale the head is. Use it to pick a chain that is actually responding. Via eth_getBlockByNumber.

Multi-hop exposure analysis over the ChainAnalyzer graph. Returns direct and indirect exposure grouped by risk tier (mixer, darknet, sanctioned entity, exchange, bridge) plus detected money-laundering patterns such as layering and structuring.

Sign-time risk verdict for a destination or spender before value moves. Registry + ScamDB lookups plus at most one RPC call (approve spender code check), so it answers in milliseconds instead of running a full scan. Same verdict as the subscription REST API.

Is this stablecoin still on its peg right now? Pass the token contract in the path and its chain as the `chain` query parameter. Returns the latest 15-minute VWAP of real DEX trades per chain, the deviation from par in the token's own peg currency (JPY or USD), and a one-word status (on_peg / watch / dislocated) at 0.5% and 2% thresholds. Reads a daily snapshot only — no external pricing call on the request path.

Is this destination a lookalike of an address the sender already trusts? Applies the address-poisoning similarity rule (leading and trailing characters that wallet UIs abbreviate to) between one destination and a caller-supplied list of known-good addresses. Pure string comparison when `known` is given, so it answers in milliseconds and never runs a scan.

Stablecoin issuer supply in one JSON call: pass the issuer as the `slug` query parameter. Returns total and circulating supply per chain, cumulative mint and burn totals, and the 20 most recent issuance / redemption events with transaction hashes. Same numbers as the public issuer page, shaped for agents.

Who is this address? Returns verified entity labels from the ChainAnalyzer known registry (token issuers, exchange hot/cold wallets, protocol deployers, sanctioned entities, mixers) plus a ScamDB hit if the address is a known drainer. TRON addresses also resolve public Tronscan tags. Unreviewed and inferred labels are never returned. 12 chains.

Screen every address a single transaction touches. Collects the sender, recipient, token-transfer endpoints and token contracts of one transaction, then checks each against the known registry, seven sanctions lists (OFAC, UK, JP, UN, EU, CA, CH) and the ScamDB drainer database. Returns one verdict: block / review / clear. Much cheaper than a full fund-flow trace because nothing is expanded beyond the transaction itself.

Top transaction counterparties for an address with entity labels, category, per-counterparty transfer counts and observed flow totals. Reuses a scan of the same address from the last 24 hours when one exists, otherwise runs a fresh scan.

Profile a Base address in one call instead of four to six lookups. Returns contract or externally owned plus code size, proxy detection across all seven slot layouts including the legacy OpenZeppelin slot Base USDC uses, the resolved implementation, ERC-165 and behavioural ERC-20 detection, token metadata, requested ERC-20 balances, and denylist hits. Answers unknown rather than guessing, and null rather than false when a contract stays silent. Not a guarantee that an address is safe.

Chainlink (LINK) price in USD now, with 24h and 7d change — Genesis402 / UnyKorn Operator Network

Compare normalized public webpage text with a prior SHA-256 hash.

Fingerprint a public page so agents can detect changes: final url, etag, lastModified, sha256 contentHash of normalized visible text, raw byteLength, and fetchedAt. POST JSON {"url":"https://example.com"}. Public http(s) only; private hosts blocked. $0.04 USDC on Base (eip155:8453). No API key.

Change watch for email deliverability report: runs the check and compares it with the result from your previous call for the same domain (kept 90 days), returning the current answer, changed true/false, exactly which fields changed with before/after values, and when it was last seen. Call it on a schedule to be told when email authentication and deliverability report for a domain in one call changes. $0.01 per check.

Change watch for has gitlab domain verification: runs the check, compares it with the result from your previous call for the same domain (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

Change watch for has notion domain verification: runs the check, compares it with the result from your previous call for the same domain (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

Change watch for has onetrust domain verification: runs the check, compares it with the result from your previous call for the same domain (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

Change watch for is email hosted by godaddy email: runs the check, compares it with the result from your previous call for the same domain (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

Change watch for is email hosted by infomaniak mail: runs the check, compares it with the result from your previous call for the same domain (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

Change watch for spf authorizes microsoft 365: runs the check, compares it with the result from your previous call for the same domain (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

Tell whether a page changed since the last time you read it. Has a page changed since you last read it? Send a URL and the content_sha256 you kept from a previous call; get back changed: true or false, the current checksum and the current length. Without a checksum, returns the starting point. Main content only, navigat…

Which South African reference series changed or were reconfirmed since a given date. The cheap cache-freshness check for agents. Optional param: since=YYYY-MM-DD (defaults to the last 30 days).

The Standard Reserve (TSR), an on-chain reserve protocol on Robinhood Chain. Governance and parameter-change history, queued changes awaiting effect, feature switches, and guardian pause state. Fields ending in _raw are 18-decimal integers as strings. Divide by 1e18 to get token amounts.

Render a bar/line/area chart to SVG (v2 discovery probe)

The Standard Reserve (TSR), an on-chain reserve protocol on Robinhood Chain. Everything relevant to deciding whether to buy into a new charter right now, bundled into one call.

The Standard Reserve (TSR), an on-chain reserve protocol on Robinhood Chain. Charters, optionally filtered by owner. Fields ending in _raw are 18-decimal integers as strings. Divide by 1e18 to get token amounts.

Generate one bounded assistant response with the operator's self-hosted Ollama model. Use for short, single-message inference where local processing is preferred. Accepts up to 8,000 characters and returns the model name, response text, and token counts when Ollama supplies them.

Claude API for AI agents, pay per token, no API key or account - POST an Anthropic Messages request (messages, system, tools, tool_choice, thinking) and get the full response back. Claude Opus 5, Sonnet 5, Haiku 4.5. Tool calling / function calling supported. Billed on actual usage at list price + 25%, capped at $0.25 per call (x402 upto scheme). LLM inference, chat completions, keyless Claude, Anthropic proxy. Free price sheet: /llm/models.

Claude API for AI agents, pay per token, no API key or account - POST an Anthropic Messages request (messages, system, tools, tool_choice, thinking) and get the full response back. Claude Opus 5, Sonnet 5, Haiku 4.5. Tool calling / function calling supported. Billed on actual usage at list price + 25%, capped at $0.25 per call (x402 upto scheme). LLM inference, chat completions, keyless Claude, Anthropic proxy. Free price sheet: /llm/models.

LLM completion per call, no account and no API key: POST a prompt (or a messages array) and get the model answer as JSON. Hard caps disclosed in every response (8k chars in, 1k tokens out on this tier). Fixed price per call, signed receipt included so the answer stays auditable. Larger tier at /x402/chat-plus.

LLM completion per call on a stronger model, no account needed: POST a prompt or messages array, get the answer as JSON. 16k chars in, 2k tokens out, fixed price per call, hard caps disclosed in every response, signed receipt included. Smaller and cheaper tier at /x402/chat.

Chat completions via Bittensor decentralized AI. Fully OpenAI-compatible. 43+ models (DeepSeek, Qwen, Llama, Mistral). Streaming, function calling, TEE-verified. Drop-in: just change base_url.

OpenAI-compatible chat completions priced from the request itself: the 402 quotes this exact body, from $0.001, and a buyer on the upto scheme settles the tokens actually used under that quote. Use it when an agent sends large or variable prompts and wants to pay for what it sends, not a flat tier.

OpenAI-compatible chat completions, premium tier: gpt-5, gpt-6 astra, o3 and o4-mini, claude opus, claude fable 5.1 - paid per call in USDC over x402. Same wire format as /v1/chat/completions with the largest caps (85k chars in, 8192 tokens out).

OpenAI-compatible chat completions, pro tier: gpt-4o, gpt-4.1, claude sonnet, gemini pro, grok - paid per call in USDC over x402. Same wire format as /v1/chat/completions with higher input/output caps (48k chars in, 4096 tokens out).

Cheap agent-ready change check for one HTTPS page. Supply 1-5 watched field baselines; returns unchanged only when every enrolled baseline is still provably present, otherwise requires_fallback without falsely claiming a change.

Cheap dated-change dual (also free at /tools/call): nearby development cases, capital projects, recent sales, FEMA events, and tax calendar. Perfect for a quick NC-area change scan. For topology-aware surrounding parcels plus multi-lane neighbors in one stored packet, prefer locus-surrounding-area-analysis ($0.10). Not a verdict. Charge-free when no component has substance.

Cheap end-to-end x402 test. Returns { ok: true, ts }. GET /v1/health/paid

Cheap generic EVM reads on Base for AI agents: native balance, nonce, contract code, ERC-20 token balance, eth_call, gas price, latest block, and transaction/receipt lookups. One call, read-only, $0.001.

Cheap wallet risk snapshot for agents: score an EVM wallet before allowlisting, paying, routing, or trading with it. Returns risk score, verdict, reasons, and compact wallet signals.

Cheapest 128k-context LLM leaderboard: the 50 lowest-cost AI models with a 128,000-token context window or larger, ranked by inference cost per token across 70+ providers. Input, output and cache USD per 1M tokens with exact context window and capability flags joined in. The standard long-document tier, priced side-by-side. Refreshed hourly.

Cheapest GPU rental rates per model (Vast.ai) — USD/day.

Cheapest LLM leaderboard: the 50 lowest-cost AI models available anywhere right now, ranked by inference cost per token across 70+ providers (OpenAI, Anthropic, Google, Meta, xAI, Mistral, DeepSeek). Input, output, cache and batch USD per 1M tokens, with context window and capability flags joined in. The one call that answers 'what is the cheapest model I can use?' Refreshed hourly.

Cheapest long-context LLM leaderboard: the 50 lowest-cost AI models with a 200,000-token context window or larger, ranked by inference cost per token — Claude 5, Gemini 3, GPT-5, Llama 4 Scout and more across 70+ providers. Input, output and cache USD per 1M tokens with exact context window and max output tokens joined in. Refreshed hourly.

Cheapest million-token-context LLM leaderboard: every AI model with a 1,000,000-token context window or larger, ranked by inference cost per token — Gemini 3 Pro, Gemini 3 Flash, Llama 4 Scout, GPT-5 long-context tiers and more. Input, output and cache USD per 1M tokens with exact context window and max output joined in. Answers 'what is the cheapest model that fits my whole corpus?' Refreshed hourly.

Cheapest-model query: returns the lowest-cost AI models matching your constraints — min_context (tokens), vision/function_calling/reasoning (true), max_input_per_mtok (USD cap), limit (default 5). Add expected_input/expected_output token counts to rank by blended USD per request instead of input price; exclude_preview=true skips pre-release models. Answers 'what is the cheapest model that can do X?' across 2,000+ models and 70+ providers.

Cheapest-model router: send your token workload and get every current LLM ranked by estimated USD cost, with per-MTok prices, cached-input rates, and context windows. Merges the weekly hand-verified llm-pricing table (every figure carrying its official source URL and verification date) with the daily OpenRouter marketplace catalog — 400+ models — and marks each row `operator-verified` or `marketplace-listed`; `verified_only=1` keeps just the first kind.…

Cheapest reasoning-model leaderboard: the 50 lowest-cost AI models with extended reasoning / chain-of-thought support, ranked by inference cost per token — o3, Claude 5 thinking, Gemini 3 Pro, DeepSeek R1, Qwen QwQ and more across 70+ providers. Input, output and cache USD per 1M tokens with context windows joined in. Refreshed hourly.

Cheapest tool-use LLM leaderboard: the 50 lowest-cost AI models that support function calling / tool use, ranked by token price across 70+ providers. Input, output and cache USD per 1M tokens with context window and modality flags joined in. The cheapest way to pick a model for an agent loop that needs reliable structured tool calls. Refreshed hourly.

Cheapest vision/multimodal LLM leaderboard: the 50 lowest-cost AI models that accept image input, ranked by token price across every provider — GPT-5, Claude 5, Gemini 3, Llama 4, Qwen VL and more. Input, output and cache USD per 1M tokens with context window joined in. Answers 'what is the cheapest model that can read images?' in one call. Refreshed hourly.