OpenAI Responses API shape, pay per request: input text or messages, instructions and max_output_tokens in, one completed message and output_text out. Llama 4 Scout by default, Llama 3.3 70B or gpt-oss-120b by model name. No account or API key; failed calls are not charged.

API recommendation. Describe a task in plain words and get the best-matching paid API calls for it from a catalog of 320 tools (web search and page reading, LLM chat, token prices and chain reads on 5 networks, sanctions and company checks, weather, finance and utilities): each pick with the exact call URL, required inputs, price, MCP tool name and whether it is in the free calls. Use when an agent needs to find which API to call before paying for one.

Everything needed to evaluate hiring or employing someone in one country, in ONE call: minimum wage, standard work week, public holidays (with in-lieu policy), parental leave, retirement age, corporate tax, business hours, banking hours and business readiness. For HR agents, EOR/global-hiring tools and payroll compliance. 195 countries with government source URLs and verification dates. Example: /api/v1/kit/hiring/DE

OpenAI-compatible moderation, pay per request: one input in, flagged and categories out (Llama Guard 3, 14 hazard categories mapped onto OpenAI names). No account or API key; failed calls are not charged.

Latest European Central Bank reference exchange rates, normalized JSON. Query: ?base=EUR&symbols=USD,GBP,JPY (symbols optional -> all). Rates update once per working day; served with a 1h cache.

Everything an agent needs to plan a trip to one country, in ONE call: visa requirements, customs duty-free allowances, tipping customs, power plugs and voltage, emergency numbers, tap water safety, SIM/eSIM options, public holidays during the stay, currency and payment culture, tourist taxes, driving side and IDP rules. 195 countries, government-sourced. Cheaper than 15 single calls. Example: /api/v1/kit/travel/JP

x402engine — OpenAI's cheapest GPT-5 tier — ultra-affordable for high-volume agent tasks

Base token risk scan: on-chain rug check and honeypot-style flag detection for any ERC-20, no GoPlus, DexScreener or other vendor - real Base token safety. Reads bytecode for mint/blacklist/pause/tax powers, EIP-1967 proxy, renounced ownership, plus Uniswap v2/v3 and Aerodrome liquidity. A Jev avoid/caution/acceptable verdict leads the response, raw signals follow. Holder concentration included only when history fits 1-2 log queries. Try GET /token-risk/sample.

Searches repository names and properties. Returns a paginated envelope with items, total, page, page_size, and total_pages, sorted by composite score.

Everything an agent needs to plan a trip to one country, in ONE call: visa requirements, customs duty-free allowances, tipping customs, power plugs and voltage, emergency numbers, tap water safety, SIM/eSIM options, public holidays during the stay, currency and payment culture, tourist taxes, driving side and IDP rules. 195 countries, government-sourced. Cheaper than 15 single calls. Example: /api/v1/kit/travel/JP

Rerank API, Cohere-style request shape, pay per request: query and up to 50 documents in, relevance scores best first out (BAAI bge-reranker-base). No account or API key; failed calls are not charged.

Real-time forex exchange rates for 170+ currencies with USD base. Daily updates from ExchangeRate-API open data. AI agent international payment calculator, cross-border FX, finance dashboard, currency converter API, pay-per-call USDC.

Validate JSON data or an API payload against a compact JSON schema and return deterministic validation results. Check required fields, value types, object structure, and structured agent inputs. Useful as a JSON validator for API responses, request payloads, and schema checks.

Amazon Autocomplete: Keyword suggestions for any Amazon domain. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Amazon: Product links, prices, ratings, delivery information, sponsored products, and more. Structured JSON, USD 0.05 per call in USDC — no API key, no account, no subscription, no minimum. Not affiliated with, endorsed by or an official channel of any of the services the results come from. All trademarks and copyright remain the property of their respective owners.

Base64 encode text or payload data, or Base64 decode a string back to UTF-8 text. Useful for Base64 encode/decode, API payload conversion, transport encoding, reversible text conversion, and decoding opaque payload strings.

GROUNDTRUTH creator counts: launches, rugged, died, active, survived, graduated, and the observed-only baseline the known_bad line is drawn from. Live fields from the mint feed every 5 s: last_mint_live, launched_live, bonded_live, mints_since_asof; ticker_asof = the newest mint seen. No mints_since_asof = not live.

Parse and evaluate a domain's SPF record: the include and redirect tree, qualifiers and the RFC 7208 limit of ten DNS lookups, with coded findings. Use when an agent must tell whether SPF is valid, why mail from a service fails SPF, or whether one more include would exceed the lookup limit.

Resolve chosen DNS record types (A, AAAA, CNAME, MX, NS, TXT, SOA, CAA, SRV) for a name through public resolvers, with TTL, observation time and the resolver that answered. Use when an agent needs the current public DNS answer for a name, for example to confirm that a record change is visible or to read a TXT verification record.

Enriched context for a single match: the teams, venue, status, and surrounding tournament state, addressable by event, event URN, or team and opponent on a date.