Compute Jaccard similarity, overlap coefficient, and Sorensen-Dice coefficient between two texts at the word level. Returns similarity scores (0-1) plus shared and unique word counts.

Calculate the precise difference between two datetimes in years, months, days, hours, minutes, seconds, and total milliseconds. Accepts ISO 8601, Unix timestamps, or natural date strings. ?from=2024-01-15&to=2026-06-23.

Generate a URL-safe slug from any string. Handles accented characters (normalize NFD), replaces non-alphanumeric with hyphens, collapses and trims. Optional max-length with word-boundary truncation.

Top N words and bigrams from text. Lowercase, strip punctuation, filter common English stop words. Returns sorted word and bigram frequency lists.

Convert arcseconds to radians (angle). Pass ?value=N.

Convert arcminutes to arcseconds (angle). Pass ?value=N.

Convert arcminutes to gradians (angle). Pass ?value=N.

Convert arcminutes to radians (angle). Pass ?value=N.

Convert text to speech using OpenAI TTS-1. Returns base64-encoded audio (mp3/opus/aac/flac/wav/pcm). 10 voices available. No API key needed; pay per call via x402. Text capped at 2000 chars.

Generate a text embedding vector using OpenAI text-embedding-3-small (1536 dimensions). Ideal for semantic search, RAG, and clustering. No API key needed; pay per call via x402. Text capped at 32k chars.

Generate a text embedding vector using OpenAI text-embedding-3-large (3072 dimensions). Higher accuracy than the small model. Ideal for semantic search, RAG, and clustering. No API key needed; pay per call via x402. Text capped at 32k chars.

Convert arcseconds to degrees (angle). Pass ?value=N.

Execute Python or JavaScript code in a secure, isolated cloud sandbox (Pro tier). Same as /api/code-run but with 60s timeout and 50k char code limit for longer computations. Returns stdout, stderr, and the expression result.

Convert text to speech using OpenAI TTS-1-HD (higher fidelity). Returns base64-encoded audio. Same interface as /api/tts but with better audio quality. No API key needed; pay per call via x402. Text capped at 2000 chars.

Compute the greatest common divisor (Euclidean algorithm) and least common multiple of two positive integers. Also reports whether the two numbers are coprime (GCD = 1).

Execute Python or JavaScript code in a secure, isolated cloud sandbox. Returns stdout, stderr, and the expression result. No setup needed; pay per call via x402. 30s timeout, 10k char code limit.

Derive a cryptographic key from a password using PBKDF2 (RFC 8018). Returns the hex-encoded derived key along with all parameters used, so you can store or verify them later. Supports sha1, sha256, sha384, sha512 digests.

LLM inference proxy (Premium tier) — o3-mini reasoning model via the same OpenAI-format interface. No API key needed; pay per call via x402. Input capped at 32k chars, output at 2048 tokens.

LLM inference proxy (Pro tier) — GPT-4o or GPT-4.1. Same OpenAI-format interface as /api/llm but with more capable models. No API key needed; pay per call via x402. Input capped at 16k chars, output at 2048 tokens.

LLM inference proxy — send an OpenAI-format chat/completions request and get a response from GPT-4o-mini. No API key needed; pay per call via x402. Supports temperature, top_p, stop, and max_tokens (capped at 4096). Input capped at 16k chars.