Every agent-payable API.

Sentence embeddings (all-MiniLM-L6-v2, 384 dimensions, L2-normalized, multilingual input works best in English) for semantic search, clustering and deduplication, or rerank mode: pass query + documents to get documents sorted by cosine similarity. Runs locally, texts are not stored. Params: texts (1 to 32 strings, max 2000 chars each) for embed mode, or query + documents (up to 64) and top_k for rerank mode.

Text embeddings (768-dim) via nomic-embed-text. POST {input: string}.

Runs nomic-embed-text locally through Ollama and returns 768-dimensional embeddings. No third-party text transfer. Input is rejected rather than silently truncated; at most four 1000-character strings per request.

Computes an exact digest for the supplied UTF-8 text. Keccak-256 follows Ethereum semantics and differs from SHA3-256. No file fetch or hash reputation lookup.

TEXT-IN ONLY sentiment trajectory: per-item score, inflection points, drift magnitude + model version. Not a trading signal. No scrape / no X. OpenRouter free-first.

Trim text and determine whether it starts with a supplied prefix.

Sentiment of English text (reviews, posts, headlines): positive/negative/neutral label, compound score -1..1 and word shares, optionally per sentence with the most positive and negative lines. Rule-based, instant.

Longest common subsequence and longest common substring of two texts, with their lengths and a 0 to 1 ratio.

Rank up to 50 candidates against a query by Jaro-Winkler, Levenshtein, Dice or cosine, best first, with scores.

Levenshtein and Damerau-Levenshtein edit distance (restricted and unrestricted) between two texts, with a 0 to 1 similarity.

Diff of two short texts into equal, deleted and inserted lines or words, with counts and a similarity ratio.

Dice and Jaccard n-gram overlap of two texts by character or word, as sets and as multisets.

American Soundex code of a name (R163 for Robert), with an optional second name to test whether they sound alike.

Original Metaphone (Philips 1990, not Double) phonetic key of an English word, with optional second word to compare.

Hamming distance between two equal-length strings (text or binary), with the differing positions. Unequal lengths are undefined.

Jaro and Jaro-Winkler similarity of two short strings (names), with matches, transpositions and prefix boost.

Cosine similarity of the word-count vectors of two texts, with shared terms and vector norms.

Uses NFKD normalization, removes combining marks, folds German sharp-s to ss, and replaces runs outside ASCII letters/digits with a hyphen. Does not transliterate every writing system.

Statistics for a text: words, sentences, characters, paragraphs, reading and speaking time, Flesch reading ease, Flesch-Kincaid grade, Gunning fog, complex-word share, lexical diversity and top keywords. Use to check copy, essays or SEO content.

Counts word-like Intl.Segmenter segments, code points, UTF-16 units, UTF-8 bytes and CRLF/CR/LF lines for supplied text. Returns the selected segmentation locale.

Text stats (demo) — Counts words, characters and sentences in a text. Demo seller for the marketplace. (community listing, paid to 0xdCbF15D032133846016377A0C78BcF068A352eC0)

Word/character/sentence counts, reading time and language stats for any text — content QA and length budgeting

Computes word/character/sentence counts, estimated reading time, and an approximate Flesch-Kincaid grade level for provided text.

Text summarization (Llama 3.2 3B): ?text=<up to 1500 chars> returns a 1-3 sentence summary. Use when an agent needs to compress a passage cheaply before reasoning over it.

Text summarization via qwen3.5-nothink:2b. POST {input: string}.

Summarize text: send any text, get a short summary written by Claude, with a word limit you choose.

Text-to-JSON extraction (Llama 3.2 3B): ?text=<up to 1500 chars>&fields=<comma-separated field names> returns a strict JSON object with exactly those keys (null when absent). Use when an agent needs messy text turned into typed structured data.

Text-to-speech API: convert up to 2000 characters into natural speech (WAV, base64) using our locally-hosted neural speech engine — no API keys, pay per call with USDC. Choose voices F1-F5/M1-M5. Use for voice agents, notifications, audio content, and IVR. Text never stored. Full 20-voice / 31-language tiered product at voice.forgemesh.io.

Convert text to natural-sounding audio via ElevenLabs (returns base64 MP3). Pay per call with USDC (x402) or credits - archtools.dev

Natural language to SQL for YOUR schema (Postgres, MySQL, SQLite, BigQuery), read-only flagged — Genesis402 / UnyKorn Operator Network

Generate an about 5-second cinematic clip from a single text prompt. Pay once via x402, then poll statusUrl for the MP4 download.

Web page to Markdown: fetch a public URL and get clean Markdown plus structured JSON (title, meta description, language, headings, tables, links, Open Graph, JSON-LD). Deterministic, no AI, fast. Respects robots.txt; you are only charged if the page was fetched successfully. (Webseite → Markdown + strukturierte Daten.)

Wandelt CSV in JSON oder JSON in CSV um, ohne KI (Convert CSV to JSON or JSON to CSV, deterministic).

Website screenshot: send a public URL and get a PNG or JPEG image of the rendered page (real Chrome, JavaScript executed) as base64 in JSON. Options: viewport width and height, full-page capture, mobile view, JPEG quality, extra wait time. Respects robots.txt; you are only charged if the screenshot was taken successfully. No logins, no private or internal addresses. (Bildschirmfoto einer Webseite.)

Base token check: send an ERC-20 contract address on Base and get verifiable on-chain facts as JSON (name, supply, owner and whether ownership is renounced, upgradeable proxy, verified source, privileged-function hints such as mint/pause/blacklist, WETH/USDC liquidity on Uniswap V2/V3 and Aerodrome) plus risk flags and a short plain-language summary. Facts only, not financial advice. Does not check holder distribution or simulate trades.

Fasst Text zusammen (Summarize text).

Translate text between 21 languages: en, de, fr, es, it, pt, nl, pl, sv, cs, el, ru, uk, tr, ar, hi, id, vi, zh, ja, ko. Runs on our own server (Argos Translate), so the text is not sent to a third party. Max 1000 characters per call. source_lang defaults to auto-detect; confidence is the detection confidence. Pairs without a direct model are translated via English.

Text translation (Llama 3.2 3B): ?text=<up to 800 chars>&to=<target language, e.g. es, fr, de, ja> returns the translated text only. Use when an agent needs quick pay-per-call translation with no API key.

Text analysis. One call to analyse a text: length, reading time and readability grade, the top keywords and repeated phrases with their density, the emails, links, phone numbers, hashtags and mentions it contains, and a prompt-injection scan for text an agent is about to act on. Up to 20,000 characters, local processing. Cheaper than the four tools bought one by one. Use to review drafts, triage inbound messages or vet scraped content.

Text classification into labels. Zero-shot classification: give text and 2-20 candidate labels, get the best label, a short reason and a ranking. Use for routing tickets, tagging content, intent detection and moderation queues.

Text classification API: classify text into your own labels with an LLM, returns the best label and a one-line reason.

Text classification API: classify text into your own labels with an LLM, returns the best label and a one-line reason.

Count characters, words, sentences and paragraphs, estimate reading and speaking time, and compute the Flesch reading-ease score and grade level for English text. Use to check the length and readability of a draft.

Summarize API, summarizer LLM: text summarization, send text and max_words, get a faithful short summary. Llama 3.1 8B inference included.

Summarize API, summarizer LLM: text summarization, send text and max_words, get a faithful short summary. Llama 3.1 8B inference included.

Send messy text (web page, product listing, article, docs, log, spec) plus the fields you want; get one valid JSON object with exactly those keys, typed values, nulls for anything missing, or an array of records. Offload parsing and save your own context tokens. Run by an AI agent.

Transcribe text to Unicode braille (grade-1 / uncontracted English braille), with capital and number signs. Characters with no grade-1 representation are clean 400s.

Turn up to 1,000 characters of text into natural speech as an audio file (base64, with its content type), in English, Spanish, French, Chinese, Japanese or Korean, with MeloTTS. Use for voice replies, audio notes, accessibility and phone or chat bots.

Use when an agent needs spoken audio from short text (voice reply, narration, accessibility). Input: text (max 500 chars), lang (en, ko, ja, zh, es, fr; default en). Output: JSON with an MP3 (base64), voice, model, safety verdict. Fixed built-in voices, no voice cloning. Text screened by Llama Guard 3; unsafe 422, not charged. Not stored. Example: ?text=Hello%20from%201gateway&lang=en

Generates a 1024x1024 JPEG from a text prompt with FLUX.1 [schnell] in about 2 seconds. Returns a hosted image URL valid for 24 hours that you can hand straight to the next tool; add inline=true to also get the base64. Choose 1-8 diffusion steps (default 4). You are only charged if the image is delivered. No API key, no account.