Web & Data

Exa neural search - AI-native web search with structured results and citations

AI text embeddings - vector representations for semantic search and RAG pipelines, pay per request with USDC

Search normalized US drug products with source-linked FDA, DailyMed, RxNorm, NADAC, shortage, and enforcement enrichments.

Web page to clean markdown. Converts any URL into LLM-ready markdown plus structured metadata — a keyless alternative to Firecrawl.

Get a product's packages, pricing, and recipient requirements before creating an invoice.

Search PyPI for Python packages — find libraries, frameworks, and developer tools. AI agent API for Python ecosystem research. Accepts USDC payments on Base and Solana

Search Semantic Scholar — 200M+ academic papers with citation graph. AI agent API for literature review and research intelligence. Accepts USDC payments on Base and Solana

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.

Comprehensive AI content analysis — sentiment scoring (-1.0 to 1.0), topic classification, named entity extraction, content type detection (news/blog/docs/tutorial), and credibility assessment. Returns structured analysis ready for immediate use. No LLM integration needed. Accepts USDC payments on Base and Solana

Check an invoice status and, with SIWX from the paying wallet, retrieve redemption codes.

Returns a list of email inboxes or mailbox accounts.

Extract structured data from any unstructured text into your own JSON Schema — structured-data / information extraction, text-to-JSON, LLM data enrichment. You supply the schema; the LLM returns a matching object. Works for contacts, invoices, events, product specs, medical records, legal clauses, resumes — any shape. Returns the extracted object plus token usage; unfound fields are omitted or null.

Extract structured data from invoice or receipt text using Claude Haiku — returns vendor, invoice number, dates, line items, subtotal, tax, total, and currency as clean JSON so agents can automate accounts-payable, expense processing, and bookkeeping from raw invoice text.

Extract structured data from any unstructured text into your own JSON Schema — structured-data / information extraction, text-to-JSON, LLM data enrichment. You supply the schema; the LLM returns a matching object. Works for contacts, invoices, events, product specs, medical records, legal clauses, resumes — any shape. Returns the extracted object plus token usage; unfound fields are omitted or null.

Extract structured data from invoice or receipt text — or directly from an invoice URL (PDF, HTML, or plain text, fetched and parsed server-side) — using Claude Haiku: returns vendor, invoice number, dates, line items, subtotal, tax, total, and currency as clean JSON for accounts-payable, expense processing, and bookkeeping automation.

List all AI models on Bittensor. OpenAI /v1/models compatible. Drop-in: just change base_url to gateway.spraay.app/bittensor/v1

Verify up to 100 emails in one call; returns a per-email record matching /verify.

Verify a single email: syntax, MX records, SMTP RCPT probe, catch-all, disposable, role-based, free-provider, typo suggestion, 0-100 score, and verdict.

Historical fiat exchange rates for a given date (YYYY-MM-DD, back to 1999-01-04) and base currency; optionally restrict to specific targets.

Validate a UK postcode and report its normalised form, format validity, and whether it is currently active.

Generate up to 20 QR codes in one call; returns a per-item record with QR metadata and the base64 PNG, or an error per item.

Check whether a domain has valid MX records and is not on the disposable list; also reports free-provider.

Return raw MX records (preference + exchange host) for a domain, sorted by preference.

Geolocate an IPv4/IPv6 address: country, region, city, postcode, lat/lng, timezone, ISP, org, ASN, and a datacenter heuristic.