All projects matching “text”

Answer a focused question from 1-3 caller-supplied text sources, with exact excerpts, source hashes, offsets, model-assessed conflicts and evidence gaps. No URL fetching or source authentication. Quote presence is checked; semantic truth/support is not independently proved. 0.01 USDC per completed brief, including insufficient/conflicting evidence; malformed output and execution failures are not s

Same as the free /v1/extract but without the 30 requests per day limit: fetch one public static HTML or JSON page and return structured data (text, attr, list, table, price, events, page, links, json) as JSON, CSV or ICS. Honours robots.txt. No JavaScript rendering. Failed calls (4xx/5xx) are not settled.

Fetches a web page server-side and returns a clean text extract with token-count estimates. Strips scripts, styles, navigation, ads and boilerplate. Served in JSON. $0.002 per call.

Search Zillow homes by ZIP code (several per run): for sale by agent, for sale by owner, for rent and recently sold, with price range, days on Zillow (1 to 90) and minimum bedrooms. Up to 25 listings in ONE call with listing status and text, home type, price and formatted price, sold price, full address, coordinates, bedrooms, bathrooms, living area and listing link. $0.025 per call = $0.001 per l

JSON canonicalization — canonicalize structured data with RFC 8785 JCS; return canonical JSON text, UTF-8 byte length, and SHA-256 hash for integrity checks, signature preparation, and deduplication. Includes an EIP-712 signed attestation. Use when an agent needs an idempotency key, cache key, dedup hash, or verifiable commitment. $0.002 per call. Free verification at POST /v1/verify.

Capture point-in-time URL facts, response headers, a text excerpt, and a SHA-256 content hash for research and verification.

Extract clean, LLM-ready Markdown or token-efficient text from any public webpage for RAG ingestion, research, summarization, or agent context. Strips navigation, ads, scripts, forms, and repeated boilerplate; preserves headings and resolved links; labels fetched content as untrusted; and returns at most 50,000 characters.

Extract text from a digital PDF into page-numbered JSON with SHA-256 hashes. No account or API key. 0.005 USDC on Base per successful document via x402. Maximum 2 MiB and 25 pages. No OCR, summaries, URL fetching, or verification of document claims.

Use to monitor or research public Telegram channels (crypto, news, project announcements, signals): pass a channel username (e.g. durov, telegram, or a t.me link) and get up to 20 recent posts with text, ISO date, view count, outbound links, forwarded-from, photo/video flags and t.me post URLs, plus the channel title, bio and subscriber count. Add q= to search posts within that channel, before= to

Use when you need what viewers say about a YouTube video, e.g. sentiment, feedback mining, FAQ or product research: up to 100 top-level comments with text, like count, reply count, relative publish time and pinned / by-creator flags, plus the total comment count. Commenter names, handles and channel IDs are intentionally NOT returned. Videos with comments off and errors are not charged.

Use when you have a likely PyPI project name (or a few tokens) and need to resolve it to live projects: tries the query as-is, PEP 503 normalization (lowercase, [-_.] → -), and hyphen/underscore/dot variants, then returns up to "limit" matching projects with summary, version, requires_python and license. This is name resolution, not full-text discovery — prefer exact package names when known. Auth

Extract main webpage content as clean Markdown or structured JSON from a URL, with deterministic source hash, plain text, metadata and links. SSRF-safe with strict redirect and document-size limits.

Build a consistent prompt set for one human character: a canonical image prompt with every appearance fact labelled, negative prompts that stop traits like glasses or a cane from vanishing, a video prompt, and optionally a contact sheet that holds everything fixed and walks one axis. Works with any image or video model. Text keeps wardrobe and framing stable; for the same FACE across images, gener

Preflight untrusted text for common prompt-injection, credential-exfiltration, and tool-abuse patterns. Deterministic heuristic scan; not a guarantee of safety.

Agent cannot hear. Send audio, get text. It never leaves this Houston box. Whisper large-v3. $0.03 USDC.

Spot FX: one ECB reference conversion, plain text. Conversion is calculated from the ECB reference rate (amount × rate). Indicative only. Not a trade quote, not for settlement. Informational only / not for transaction use. Source: ECB statistics. These reference rates are free at https://www.ecb.europa.eu (and via Frankfurter). Not sold or endorsed by the ECB.

x402 MCP Tools: Generate a QR code (URL, text, vCard or WiFi) as a base64 PNG.

Compress long text into key sentences for agents that need a short digest without calling an LLM.

Cryptographic hash of a text string - sha256 (default), sha512, sha1 or md5 - returned as hex and base64. Use it for content fingerprints, integrity checks and deterministic ids; pure computation, instant.

Parse a freight rate confirmation (PDF or text) into structured JSON — freight.parse_ratecon

GPT-OSS 120B open-source language model API - high-quality text generation without API keys

Generate AI hairstyle from text prompt

Translate text between languages (LLM, structure and placeholders preserved) (1 × 1,000 characters at 0.030000 USDC each)

Extract named fields from unstructured text into strict JSON. Use when an agent must turn an email, filing, invoice, or description into {field: value} records up to 4,000 characters.

Invoice or receipt (PDF, PNG/JPEG/WebP image, or plain text) to structured JSON with a fixed schema: vendor (name, address, VAT ID, email, phone, IBAN), customer, invoice number, order number, issue/due date, currency (ISO 4217), subtotal, VAT total, total, amount due, VAT breakdown and line items. Every field has value, the verbatim source quote and a confidence score (0-1: quote found in the doc

Extract and validate structured expense data from receipt text or a provider-neutral receipt extraction. Use when an agent needs merchant, date, tax, total, line items, confidence, duplicate detection, and arithmetic validation before creating or reconciling an expense. The result is advisory and always requires human review.

SHA-256 of text encoded as UTF-8 (maximum 1024 bytes). Costs 0.01 USDC.

Readable text from a public webpage

Check a Base or BNB Chain (?chain=bsc) address before you pay it: a verdict label pay / hold / unknown with a human text (Pay, Hold, Inactive, No track record or Couldn't check) and the one reason, such as active with real counterparties or a high-severity flag named. Under it, the evidence: every flag with its source, what was not assessed, and the EAS attestation if one exists. On-chain behavior

Compare text using deterministic, case-insensitive bag-of-words token-overlap similarity for lexical duplicate screening. Lowercase each input and tokenize with Python Unicode regex \w+ (letters, digits and underscores). Count repeated tokens. Similarity = sum(min(count_a(token),count_b(token))) / max(words_a,words_b,1), rounded to four decimal places. Returns exactly similarity in [0,1], words_a