Explore APIs

LLM inference API: OpenAI-compatible chat completions for 100+ AI models (DeepSeek, GPT, Claude, Gemini, Grok, GLM, Qwen, Kimi, Llama, Mistral). Suited for AI agents that need on-demand text generation, coding or tool calling paid per request in USDC on Base with x402: no account, no API key. Model in body.model (GET /v1/models); streaming supported. Exact price in the 402 quote; automatic refund

Genuinely fascinating fun fact about science, history, nature, or the universe.

Divides each available substrate mass by its required mass per product mass, selects the limiting substrate, and applies a caller-supplied process efficiency. It does not model yeast metabolism, kinetics, oxygen transfer, toxicity, regulation or actual fermentation performance.

HISTOR pre-flight for an MCP server: its signed record in the HISTOR transparency log — when the tool set was first seen, whether it changed, what the pattern scan found. Never contacts the server asked about.

Paste-ready bid draft (0.01 USDC cheapest). Free radar first: GET /v0/sample-radar then POST {brief}.

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.

Split an IPv4 or IPv6 CIDR block into subnets of a longer prefix, in order, at most 256 at a time; a larger split is refused before anything is computed. Offline. Use when an agent must plan an address layout or hand out subnets. Input: ?cidr=192.0.2.0/24&prefix=26.

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

Live call volume and revenue analytics across all WorxAI x402 endpoints — total settled calls, USDC revenue, page/AI-visitor traffic, and a per-endpoint breakdown. Useful for agents benchmarking or auditing this API before committing to a larger dataset purchase. Analytics access costs $0.035 per delivered row per successful call.

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

DripMetricsAI (api description at https://dripmetrics.ai/) provides on-demand market microstructure and risk metrics for agents and developers. Agents can pay per request via x402 and receive structured JSON metrics without subscriptions or API keys. VPIN measures volume-synchronized order-flow imbalance (an adverse-selection proxy, not a probability); see excessVpin. Discovery examples use the la

Fact-checking and claim verification API for AI agents. Verify whether a cited source supports a claim; check statistics, dates, units and populations in research reports before publication. Separate web research returns a verdict, linked evidence and sources. Source verification is model-assessed, not guaranteed correct. POST /v2/verify; x402 v2 on Base; 0.20 USDC. No signup or API key.

Official HivemindOS paid agent (default)

Deterministic text normalization: Unicode NFKC, zero-width/bidi stripping, smart-quote and dash folding, whitespace collapse, case folding. Returns a stable content hash so two texts can be compared for exact equality.

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

Automated TypeScript/Zod, Python Pydantic v2, and JSON Schema (Draft 2020-12) code generator microservice. Converts raw JSON payloads, API responses, or JSON Schemas into strict, ready-to-use Zod schemas, TypeScript interfaces, and Pydantic BaseModel classes with automatic format detection (UUID, ISO-8601 datetime, email, URL, EVM address) and nested object extraction.

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.

No description yet.

Text completion using the model selected in the request body.

One original constraint card in the tradition of lateral-thinking decks: a short instruction, reversal or question you can apply to whatever is stuck, written fresh by a model at high temperature on every call. The cards are ours, never a card from any published deck. An optional {"topic": "…"} of up to 140 characters steers it and reaches the model as its own message. No pool, no cache, and nothi

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.

Student discounts / college student deals / verified student savings by category. Returns the best current verified student discounts for a category, with how to verify student status to claim each. For shopping and savings agents.

Converts text, JSON or JSONL to cleaned JSONL using fixed rules. Removes empty, short and duplicate rows; can repair some encoding issues. No AI or CSV parsing.

OpenAI-compatible chat completions on frontier models: GPT-6.1 Sol and Terra, GPT-5.5, Claude Sonnet 5.5 and Haiku 5.5, Gemini 3.8 Flash, Grok 4.7, GPT-6 Luna, gpt-oss.

Call before your agent pays an x402 service it has not used recently: is that endpoint actually alive? Liveness of the ~200 most recently updated Bazaar listings, probed in rotation (each about every 36h): HTTP status, latency, last-OK time and consecutive failures per endpoint. Measurements only, no judgements; the probes never pay. Free aggregate view: gblin-mcp.gblin-mcp-worker.workers.dev/cata

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

Curated aesthetic-medicine brand directory, partially verified. One call returns the full core catalog of filler, toxin, and thread brands: name, manufacturer, country, categories, certifications, treatment areas, and verification status. Some fields may be null.

Extract strict, JSON-Schema-valid typed JSON from unstructured text or HTML. Failed extraction calls are not settled. Primary x402 V2 API for production agents.

Is wildfire smoke affecting the air here right now? Smoke tracker — AQI estimate, nearby active fires, health risk level, mask and indoor-air guidance, and evacuation status for any location.