18 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.
Multi-oracle price consensus (?symbol=SOL|BTC|ETH): median across Pyth, Binance, Coinbase, Kraken and CoinGecko queried in parallel, with spread in basis points, outlier detection for stale or manipulated feeds, per-s...
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.
Convert text into a 768-dimension embedding vector (nomic-embed-text) for semantic search, RAG retrieval, clustering, deduplication or similarity scoring. POST JSON {"input": string}, up to 3000 characters; returns {embe...
AI text summarization and analysis (Qwen3-4B, local). Send any text in the 'texto' field (you may start it with an instruction, e.g. 'Summarize in 3 bullets: ...') and get a concise summary or analysis in the same langua...
CUDA, driver and Ollama compatibility - GPU support, model memory fit and proof inference uses the GPU
Federal Register activity on a topic: what published recently, final vs proposed, which agencies, what takes effect.
AI summary of any public webpage: fetches the URL, extracts readable content, and returns a short, medium, or long factual summary.
Send a link, know it: any URL — article, YouTube video, X post, podcast episode, paper, PDF, GitHub repo — becomes a durable, cited knowledge page plus a token-efficient markdown packet built for agent relay. Flat $0.01...
Argentina official gazette (Boletin Oficial) keyword search returning literal excerpts of matching notices with dates and source URLs; an optional date limits the search to that day's notices. Use this when an agent need...
Turns text into speech with Amazon Polly and returns a signed URL of the audio, valid for an hour. Up to 3000 characters with standard voices or 1000 with neural ones. Voices include Joanna, Matthew (English), Mizuki, Ta...
Get the full text of one web page. Give a URL; returns the page's own main content as clean markdown (up to 8,000 characters) with navigation and ads removed, unchanged and not summarized (use /summarize for a short vers...
Wandelt CSV in JSON oder JSON in CSV um, ohne KI (Convert CSV to JSON or JSON to CSV, deterministic).
Summarize a URL, raw text or HTML at the length you request - short, medium or long - with the source noted. Neutral and factual, no invented facts. Try GET /summarize/sample. Part of the AgentIndex content kit (pdf, web...
Summarize long text: paragraph, bullets or TL;DR with a word limit — Genesis402 / UnyKorn Operator Network
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,...
Token compression for LLMs
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.
Summarize a text or a web page (LLM, word limit, key points) (1 × 5,000 characters at 0.040000 USDC each)