Shame I already rolled this out in-house (and spent way too long trying to achieve it) - this would have been perfect for my use case. If you don't mind me asking, how do you get chrome to boot so quickly? GCP is unbelievably good at launching containers quickly but chrome is slow to launch.
Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
11–20 of 46 posts
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#12Shame I already rolled this out in-house (and spent way too long trying to achieve it) - this would have been perfect for my use case. If you don't mind me asking, how do you get chrome to boot so quickly? GCP is unbelievably good at launching containers quickly but chrome is slow to launch.
We actually keep a pool of browsers ready so when a request comes we just assign it to an already running browser. This way in most situations there is no actual waiting for chrome to startup!
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#13Your pricing is too confusing. Either price it based on number of requests like ScrapingBee does, or base it entirely on bandwidth. Instead your pricing is based on both bandwidth and “minutes” (which is also hard to predict when some sites can load slower than others)
2nd, the pricing also seems way way below what ScrapingBee offers.
You charge $100 for 60K credits. So assuming 18 credits for 1 page (3 MB per page) that allows me to crawl 3333 web pages. $250 would allow me to crawl under 10k pages
In comparison it costs $249 for 3 million credits in ScrapingBee which enable me to crawl 100,000 webpages (with JS and proxies enabled)
Am i missing something obvious here?
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#14Shame I already rolled this out in-house (and spent way too long trying to achieve it) - this would have been perfect for my use case. If you don't mind me asking, how do you get chrome to boot so quickly? GCP is unbelievably good at launching containers quickly but chrome is slow to launch.
We actually keep a pool of browsers ready so when a request comes we just assign it to an already running browser. This way in most situations there is no actual waiting for chrome to startup!
Ah of course, makes total sense. Thanks for answering!
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#15Shame I already rolled this out in-house (and spent way too long trying to achieve it) - this would have been perfect for my use case. If you don't mind me asking, how do you get chrome to boot so quickly? GCP is unbelievably good at launching containers quickly but chrome is slow to launch.
What challenges did you face in rolling this out? I did as well, and it didnt take long but thats only because I didnt aim for 100% perfection and was OK with being able to crawl 90% of webpages i encountered
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#16Your pricing is too confusing. Either price it based on number of requests like ScrapingBee does, or base it entirely on bandwidth. Instead your pricing is based on both bandwidth and “minutes” (which is also hard to predict when some sites can load slower than others) 2nd, the pricing also seems way way below what ScrapingBee offers. You charge $100 for 60K credits. So assuming 18 credits for 1 page (3 MB per page)…
Hey! Completely hear you on that, right now we just have endpoints for headless browsers, this is a instance running chrome with dedicated resources that you have full access to. This comes with proxy services and captcha solving. This comes at a higher cost but you will get blocked less and can do much more, like browser automations.
Dedicated endpoints for just scraping like scraping bee are coming next week at a discounted price! In the mean time let me know if there is anything you would like that scraping bee is missing :)
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#17Your pricing is too confusing. Either price it based on number of requests like ScrapingBee does, or base it entirely on bandwidth. Instead your pricing is based on both bandwidth and “minutes” (which is also hard to predict when some sites can load slower than others) 2nd, the pricing also seems way way below what ScrapingBee offers. You charge $100 for 60K credits. So assuming 18 credits for 1 page (3 MB per page)…
Hey! Completely hear you on that, right now we just have endpoints for headless browsers, this is a instance running chrome with dedicated resources that you have full access to. This comes with proxy services and captcha solving. This comes at a higher cost but you will get blocked less and can do much more, like browser automations. Dedicated endpoints for just scraping like scraping bee are coming next week at a d…
Thanks, ScrapingBee has everything I am looking for in terms of functionality. My honest opinion is that most people who are looking for an alternative just want something cheaper. Thats 99% of what I am looking for, at least
Things like captcha solving are nice no doubt but for many people, their use cases just aren’t compelling enough to make it worth the ROI. I would love captcha solving, but definitely not at your price point..
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#18Earlier quoted context omitted.
Hey! Completely hear you on that, right now we just have endpoints for headless browsers, this is a instance running chrome with dedicated resources that you have full access to. This comes with proxy services and captcha solving. This comes at a higher cost but you will get blocked less and can do much more, like browser automations. Dedicated endpoints for just scraping like scraping bee are coming next week at a d…
Thanks, ScrapingBee has everything I am looking for in terms of functionality. My honest opinion is that most people who are looking for an alternative just want something cheaper. Thats 99% of what I am looking for, at least Things like captcha solving are nice no doubt but for many people, their use cases just aren’t compelling enough to make it worth the ROI. I would love captcha solving, but definitely not at you…
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 :)
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#19Hi,
This looks very interesting and I’d love to try it.
We have data extraction and enrichment platform. We process over 12 million automations for our users, half of this is done on lambda and rest we try to process in a container.
We also utilize 10 GB+ in proxies.
I tried to do all the math on how much it would cost on your platform if we do a pilot project but I’m so confused with the pricing.
Can you please explain for 10,000 hours and 10 GB proxy usages what would the cost?
Re: Show HN: Hyperbrowser – Scalable Browser Infrastructure for AI Apps
#20Hi, This looks very interesting and I’d love to try it. We have data extraction and enrichment platform. We process over 12 million automations for our users, half of this is done on lambda and rest we try to process in a container. We also utilize 10 GB+ in proxies. I tried to do all the math on how much it would cost on your platform if we do a pilot project but I’m so confused with the pricing. Can you please expl…
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!