Octen
Octen Broad Search
/broad-search
Broad web search — decompose a query into sub-queries from multiple angles and search concurrently.
from $0.0010per result
0 Markup
Octen
Octen Web Search
/search
Real-time web search across the live internet, with filters, highlights, and full page content.
from $0.0010per call
0 Markup
Octen
Octen Embedding
/embedding
Convert text into embedding vectors.
$0.01–$0.07per 1M tokens
0 Markup
Octen
Octen Extract
/extract
Extract clean, LLM-ready markdown from web pages — up to 20 URLs per call.
$0.0010per result
0 Markup
Try it with your agents
01
Map a product's competitors
Set up https://monid.ai/SKILL.md, and then use Monid to search the web for the strongest alternatives to Notion and build a comparison table from the top sources.How-to guides
Which model should I use?name the board, because two boards crown two modelsget the lmarena code leaderboard from monid and give me the top ten with their ratings and vote counts. label it as crowd elo on coding tasks and tell me today's date, because the payload has no timestamp in it what this is: crowd Elo from head-to-head votes on coding prompts, run by LMArena, as it stood on 2026-09-25 what it is not: a measurement of your task; the prompts are theirs, the voters are theirs, and neither is your codebase the spread: 751 rating points between first and last across 134 models, which is a real gap, unlike the gaps at the top the missing field: no timestamp anywhere in the payload, so the pull date has to be recorded by you, not read off the responseHow do I read any web page as clean text?free route first, escalate on a thin answerread <url> as markdown with context.dev on monid and keep the code blocks, then count the fenced blocks against the page and tell me the number. do not judge it by the character count: link syntax and page chrome are included by default and can make the output larger than the visible text the cheap one: 15,312 characters with all three code samples intact, plus the page metadata the 66x one: 9,948 characters and every code fence stripped to prose what that means: on a documentation page, the expensive extractor lost exactly the part you came for count blocks, not characters: on a second page all 32 code blocks came back and twenty sampled ones were verbatim, while the character count was 74% larger than the visible text because link markup and chrome are on by default and made up two fifths of the output and the length field is bytes: the endpoint's own content length is counted in utf-8 bytes rather than characters, so it will not match a character count either the tie: on a news article the cheap one and a near-free one returned the same text, neither blocked