43 services carry this tag in their source record. Tags come from the provider, not from us — a tag is a claim about what the service does, not proof that it does it well.
Rewrites Brazilian Portuguese text into European Portuguese (Portugal): vocabulary, gerund → 'a + infinitive', 'você'. Rule-based detection, local LLM rewrite, re-check of remaining BR markers. Returns unchanged text (fr...
Base Latest Block: current Base mainnet block number, timestamp, base fee and gas used. $0.001 per call.
Store an object (up to 1 MB, up to 30 days) in James's private bucket. Only the paying wallet can read or delete it back (signed request, no public URL). Pay per write in USDC.
Text to speech for agents: send text (up to 2,000 chars) in English, Spanish, French, Chinese, Japanese or Korean and get a WAV voice clip (base64 in JSON, or raw audio/wav with response_format=wav). $0.001 USDC per star...
Wandelt CSV in JSON oder JSON in CSV um, ohne KI (Convert CSV to JSON or JSON to CSV, deterministic).
Translate Mandarin Chinese (Simplified or Traditional) into clear, natural American English: plain text by paragraph, or SRT/WebVTT subtitles returned in the same format with timings kept. Names, numbers, dates and units...
Translates text between about 100 languages with Meta M2M100 1.2B: pass the text and the target language (ISO code like es, fr, de, zh, ja, or its English name); the source language is detected if omitted. Long texts are...
Detect the language of a text among 55 languages, with probabilities for each candidate and a reliability flag. Use to route messages, pick a translator or tag content.
Translation for agents handling multilingual DeFi content: converts protocol docs and error messages across languages with tone control and auto source-language detection. Category: inference.
Convert Serbian text between Cyrillic and Latin script.
Translation API: translate text into 15 languages (English, French, Spanish, German, Italian, Portuguese, Dutch, Polish, Russian, Ukrainian, Turkish, Arabic, Chinese, Japanese, Korean), source language auto-detected, up...
Translate text into any major language, preserving names, numbers and formatting — Genesis402 / UnyKorn Operator Network
Takes two documents, by URL, inline base64 or raw text, extracts the text of each and compares them. Paragraphs are the unit: the answer lists every block that was removed, added, or kept but reworded, and for reworded b...
OpenAI-compatible chat completion with Qwen3 30B (fast mixture-of-experts model): set the base URL to /v1/llm/qwen3-30b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call,...
Drop-in OpenAI Embeddings endpoint: POST {input: string | string[], model, encoding_format: float|base64, dimensions} and get {object: "list", data: [{embedding, index}], model, usage}. Models (Cloudflare Workers AI): bg...
Text embeddings with bge-m3 (1,024 dimensions, multilingual): one text, or up to 32 texts in one call (POST texts array), up to 32,000 characters in all. For semantic search, clustering and similarity.
Base transaction explained from the chain: success or reverted, block and time, from, to, ETH value, method selector, gas used and fee, contract created, and every ERC-20 transfer decoded with token symbol and amount. In...
AI batch: run summarize, rewrite, sentiment, keywords, classify or outline on up to 50 texts; returns results in order.
Summarize a text or a web page (LLM, word limit, key points) (1 × 5,000 characters at 0.040000 USDC each)