Launched this week
Octen
We stayed quiet and built the FASTEST AI search on Earth
89 followers
We stayed quiet and built the FASTEST AI search on Earth
89 followers
Octen is a search API built for AI agents, not humans. Instead of one query at a time, it decomposes a question into sub-queries, fires them all at once, and returns results in 62ms (P50), several times faster than other providers. Pricing is $1 per 1,000 calls, well below typical rates of $4 to $9. A single account handles over 1,000,000 queries per second, with new content indexed within 5 minutes. Our embedding models rank #1 on RTEB and MMEB-v2.
Hey Product Hunt 👋
I'm Kuan, founder of Octen. Before this, I led AI search product at Alibaba Cloud and built Baidu's enterprise search platform, so I've spent a decade dealing with search infrastructure that had to survive real scale.
When I looked at the search APIs being handed to AI agents today, I was surprised. Most are the same human-search stack wrapped in an endpoint, and many start to break once you push tens of queries per second. But an agent doesn't search the way a person does. It wants to ask a question from many angles at once and get everything back together.
So we rebuilt search from scratch for that use case. Octen decomposes a query into sub-queries, fires them concurrently, and returns results in 62ms (P50) and 68ms (P90) on SealQA Hard, several times faster than other providers in this space, at $1 per 1,000 calls instead of the usual $4 to $9.
We spent the past several months building this quietly because we didn't want to make noise before the numbers were real. All benchmarks are public and reproducible (link in the post). Would love for you to run it against whatever you're using today and tell us what you find.
Happy to answer any questions here.
Currently as an engineer building at Octen, I excited for our launch. I have been applying our search capabilities to wearables and AR, and that's where latency actually bites. When a device is reacting to what you're looking at, search that takes a second breaks the whole thing. Sub-100ms is what makes it feel like it just knows.
I'm on the team here 🙌 Been heads-down on this for months. The 62ms P50 is the number I'm proudest of — and just as important, every benchmark behind it is public and reproducible. Like Kuan said, we stayed quiet until the numbers were real. If you run it against what you're using today, please tell us where it falls short; that's exactly the input we want. Congrats to the whole crew, and thanks Kuan for leading it.
As a product manager on the team at Octen, I'm so excited to see this go live.
I've been applying our search to AI agent pipelines — where one task fans out into dozens of sub-queries. Latency doesn't add up there, it multiplies. Getting each call under 100ms is what makes the whole thing feel alive instead of frozen.
Give it a try — would love to hear what you build with it.
AVI by True AI
65ms is the part that really caught my attention. In something like a voice agent or a multi-agent workflow where one agent is constantly handing off to another, latency compounds very quickly. Keeping each call this fast could make the difference between a demo that looks good and an app that actually feels usable. Definitely trying this with my current app! Congrats on the launch!!
Honestly the sub-query thing is kind of clever, I tested it on a research prompt and it came back faster than I expected. Price point looks solid too.
@gzdexquf Thanks for actually testing it, Gözde. Sub-query decomposition is especially useful when a research prompt spans several angles. If you try more prompts, we’d love to hear what worked and what didn’t.
Congrats on the launch! The agent-first framing makes a lot of sense — most search APIs really are just human SERPs with a JSON wrapper, and they fall over the moment you fan out queries. The $1/1k pricing is aggressive enough that I'll definitely benchmark it against what we're using now. Appreciate that the benchmarks are public and reproducible — that's rarer than it should be.