shrisukhani

In our (very) early testing at Hyperbrowser but we're seeing Haiku 4.5 do really well on computer use as well. Pretty cool that Haiku is like the cheapest computer use model from the big labs now.

+1 on this. Improving Gemini apps and live mode will go such a long way for them. Google actually has the best model line-up now but the apps and APIs hold them back so much.

Welcome tomho!

MCP is now the standard everyone must conform to. Couldn't possibly have predicted that 2 months ago.

Super cool. Congrats on the launch!

Let me know if we can help with something at Hyperbrowser.

This looks really neat. Curious if you can say anything on how it's different from puzzle.io?

No, we don't enforce any robots.txt restrictions ourselves. We also don't do any scraping ourselves. We provide browser infrastructure that operates like any normal browser would - what users choose to do with it is up to them. We're building tools that give AI agents the same web access capabilities that humans have, don't think it's our place to impose any additional limitations.

Thanks! :)

Thanks!

And yeah MCP is super promising. We announced this on X and LinkedIn yesterday and the response has been really good. A lot of people with a bunch of use cases.

One surprising thing is there’s also a bunch of semi/non-technical people using our MCP server and the installation experience for them rn just absolutely sucks.

I think once auth and 1-click install are solved, MCP could become the standard way to integrate tools with LLMs

Thanks!

1) Yep, you just pay from browser time and proxy usage

2) We use a handful of proxy providers under the hood ourselves. There’s a lot of shady ones but we only work with ones where we’ve vetted the source of. Different providers source proxies in different ways - directly from ISPs, paying end sources for proxies etc

Curious what people think about the CUA API pricing? Any thoughts on what use cases it may or may not work for (the pricing specifically)?

ya i'm sure they'll get a bunch of usage despite that but don't know who would use it at any kind of scale with that pricing

otoh, they've dropped prices for everything else a ton previously so maybe they will for this as well

Interesting. Thanks for sharing!

Nice. What'd you think of it?

I’m a happy Cursor user. Main reason is it just works great and was the first one I tried.

Pretty excited for this but looks like the testing program is still behind a waitlist - even for Google One subscribers

Anecdotally, we also found Gemini Flash to be better.

This is really neat guys - congrats!

Congrats on launching guys!

So many people building with / on top of browser-use now - spawned a whole cottage industry! :)

this is neat - congrats!

Neat! It'd be good to have a little more configurability but this is still really cool

Looks super cool. Congrats and best of luck!

Curious if there's anything built with Eliza outside of crypto twitter agents

Cool project either way!

Pretty wide variety of use cases tbh - everything from classic scraping on the very simple side to integrating with 3P services that don’t offer APIs, agentic QA testing etc

The companies we’ve seen automatic agentic workflows well typically send a bunch of context to the LLM and somewhat constrain the actions that the model can take. Actually works better than you’d expect :)

Yup! We need to add it to the docs in a day or two but happy to help do it myself. Drop me a line at shri@hyperbrowser.ai!

thank you! :)

Sorry - Cloudflare bypass is coming this weekend!

This is also something I need btw so if you built a product on top of it, I'd be user #2 :)

Hey - thanks!

For your specific example, this is how the math works out:

- Browser hours: 10K hours * 60 minutes per hour * 1 credit / minute = 600K credits

- Proxy usage: 10GB proxy data * 1024 MB / GB * 6 credits / 1MB proxy data = 61,440 credits

The scale plan includes 60K credits for $100/mo and overage credits are ~0.2c each, so the total would be $100 + (601.44 * $0.002) = 1302.88

Sorry about the confusing pricing btw! As I wrote this out, clearly we have our work cut out for us to simplify pricing - we'll try to make it simpler over the next few days and add a calculator that let's you see how much this would cost.

Feel free to email me at shri@hyperbrowser.ai if I can help with anything!

Other cofounder of Hyperbrowser here - thanks for the feedback, and noted!

We aim to be pretty competitive on price across the board. Today we're just launching our headless browser service and I think we're significantly less expensive than competitors on that as dbmikus mentioned below

Totally hear you on the scraping specific use case without captcha solving etc though - we'll probably launch competitive pricing for this specific use case in the next few days. I'll make a note to leave a comment here when we do or feel free to email me at shri@hyperbrowser.ai and I can follow-up there :)

update: fixed now :)