Update to Kagi Search Pricing | Hacker News Reader

Update to Kagi Search Pricing

blog.kagi.com

204 pointsexists231 comments

I cancelled by Kagi subscription because of this.

I don't want to have to pause before I search and think "do I need to search for this? should I look through my bookmarks, notes, etc? is this worth one of the 7 searches my $5 plan will cover for the day?".

I've been a frequent user of Kagi for the past ~9 months. Last month I made 1600 searches.

I've even 'tipped the difference' (~$70) in the past to support Kagi. It feels gross that they're now upcharging me despite the goodwill I showed them. I know they're a business, but if you're a business, and you're not willing to respect your users, then don't ask for donations.

I hope that something better than Google comes along. It was Kagi, but now it's back to the drawing board for me.

My advice to Kagi: make searches cheaper. This product has no future otherwise.

I was finding it hard to justify the current price. This new pricing is madness to me.

I think their rationale about the 'average number of searches' is misguided - what about the average number from people who are Kagi users? Those are the ones willing to pay for search, which I'd argue are currently not the 'average internet user'.

In the FAQ they they mention the average Kagi user does 700 searches a month. Perhaps uncoincidentally, the $10/month plan includes exactly that many searches.

I hope it will be possible to transfer unused searches from the current month to the next. If I have 400 in February and 760 in March it would be very annoying to suddenly be forced to pay or need change back to Bing.

It will not be possible.

https://blog.kagi.com/update-kagi-search-pricing#faq (Third question.)

The justification they give seems to be nonsense: "While we understand that this may be inconvenient for some users, it’s important to note that providing free trial accounts and supporting our team members’ salaries requires a delicate balance. "

Well that's a waste. I'll see how it goes but if it annoys me I'll cancel the subscription.

It does appear that my current usage (as confirmed on their linked dashboard) will be covered by $10/mo plan I'm already effectively on.

Without even considering the early adopter benefit, this pricing update for me is a nothing-burger.

I am exactly in the same boat. I had raised my concerns regarding pricing twice and both the times they had said that they will introduce new pricing model. I was really hoping that they will reduce my $10/mo subscription pricing.

It’s a classic startup mistake – alienate your current evangelical users so you can appeal to the (uninterested) masses. Paul Graham has a line about how you should aim for a deep but narrow well rather than a wide but shallow one. Sad that Kagi hasn’t realised this and decided to plough ahead with this ridiculous strategy.

Sorry I don’t understand this POV.

We know Kagi is losing money on that pricing. ( They have stated it multiple times ). They offer options to donate for those willing to help and chip in.

They now updated the pricing model. They gave you extra 300 on top of their current pricing. The extra 600 search will only cost you $9 more, slightly more than what you tipped them.

So what is wrong ?

And you are supporting their browser development. I mean I understand people want unlimited, but then you are already tipping them. So something must be missing here I am not getting it.

How do you see they give extra?

With the old pricing, it's unlimited searches for 10$ a month. With the new pricing, you're now limited to 1000 for this price.

They are giving extra when you factor in the donations. The old pricing was losing money.

The top poster doesn't seem to think the price should even cover kagi's costs, which is absurd.

> The top poster doesn't seem to think the price should even cover Kagi's costs, which is absurd.

No, they definitely should cover their costs. They're a business.

But, the cost they're charging is too much. I don't care how much it costs you to perform a search, I care how much it costs me.

They have every right to cover their costs but I don't appreciate the bait and switch. It seems like a desperation move since I don't see how they can sustain and grow their user base at these price points.

You're right that the cost is more or less the same. The problem is that they burned a lot of goodwill.

> The extra 600 search will only cost you $9 more, slightly more than what you tipped them.

I _chose_ to pay more not because I value search at that price, but rather because I liked Kagi and wanted to support them. I'm not going to be forced to pay $20/mo (or whatever it ends up being) for search.

> And you are supporting their browser development.

I tried their browser. I didn't like it.

It's a 150% price increase if you don't want metered search. I probably would have been ok with a reasonable price increase, maybe 25% to 50%. But it's a lot to ask of your users when most of us have to manage a number of subscriptions and almost all of them have had price increases over the past year.

Just speaking for myself, I don't care about their browser or "AI" features. Paying more for search to subsidize those projects is a turn off for me.

I think what becomes clear from this price increase is how expensive search is.

Google seems to be free, but they are making a profit by gatekeeping the internet. If you offer a product or service, and you want people to find your restaurant, your hotel, your guided tour, your private tutoring lessons, or anything else, you pretty much have to pay Google.

It's kinda like the Yellow Pages, except 100x more expensive.

If you as a user don't want your search results dictated by who pays the most, it's going to be expensive.

I'm paying ~10 bucks for spotify to stream music non stop. I'm also paying netflix some ~16 bucks for 4K movies/series. There's no way a text search is more expensive than a 4k, 5.1 channels movie.

I'm using Kagi since they were in beta, but as soon as my subscription expires, I'm done...

It certainly can be more expensive than streaming. Bandwidth is very cheap. (Cloud provider bandwidth charges are completely artificial and pure profit.) Search requires a lot more compute and fast storage as well as more developers since it’s a much harder problem.

Arbitrary and quite possibly unique searches over substantially all knowledge ever produced by humanity seem a lot harder than sending an unchanging large file over a network.

And since Bing rasing prices affects their price so much, I'd argue that Kagi isn't investing enough into their own crawler/index, so that they can ultimately bring down the price of search.

Instead they're integrating yet another third-party (OpenAI), thereby rasing the price even more and tying their price to third-party API pricing even more.

I find the pricing more annoying than anything. I'm a paid user and I've never come close to using more searches than their claimed cost (which admittedly I don't understand fully, is it just the marginal cost?) So I could probably pick a lower usage plan, it's just one more thing to think about, like back in the days of having to decide which phone minutes plan is better. It sows confusion and doesn't benefit the customer. Maybe they should add a "my five" top searches that are free.

I know people will say it's not a big deal, but it's more friction.

Also as I've said before, I have no interest in paying for any of the "AI" features. I haven't looked closely enough to understand if these costs are baked into search query costs now, but any suggestion I have to pay to have Eliza read me my search results is a dealbreaker for me.

Replying to myself re the "AI"

The Kagi announcement says this is what it will cost

  Summarize results: 0-1 searches

  Summarize document: 0-20 searches (depending on length of the document, this can process 100 page research papers or even books)

  Ask questions about document: 0-20 searches (depending on the length of the document and the length of interaction)

So it's optional, however they also say this:

  However, incorporating generative AI into search can be expensive, so we had to consider this in our pricing model.

Which implies that it's making everything more expensive.

I was thinking about the decision to add this AI stuff - I guess I see why they did it, they say it's always been part of the vision and pressure (even internal) to add such features and not feel like they're falling behind other offerings must be intense.

Personally I think it's a mistake. "Generative AI" has instantly become dime-a-dozen and everybody and his dog has a startup competing in this space. Another me-too offering doesn't add to this. Good paid search was an almost open playing field, which is what made kagi so special in the first place. I think they could have focused on doing this well (and reducing costs).

Wasting money and time on the AI integration was a huge mistake. If I want ChatGPT to hallucinate a page for me, I can cut-and-paste it myself.

I won't be cancelling now as I seem to be averaging a bit more than 1000, meaning pricing will stay about the same since I should get the early adopter subscription.

However, the "average amount of searches" they're stating really can't be accurate for any tech savvy user who is using it professionally and privately. It really has to become cheaper, if it doesn't I sadly don't see myself using it long-term.

When I saw this my initial reaction was to cancel, then I checked my usage with the early adopter professional plan it seems I'm mostly covered with 1000 searches a month inlcuded in the $10 subscription. Maybe some months I'll incur a small charge but nothing over $14 I don't imagine.

I could also reduce the cost pretty easily if I'm honest. I could stop searching for a site and clicking the result rather than entering the URL or using a bookmark. I could use a sites search function more often too rather than searching kagi for website name + keyword.

Some years ago I moved to a house with a water meter, previously I paid a flat rate and could use as much water as I wanted. I wasn't happy at first, but when I thought about it, being mindful about how much water I'm using is a good thing. Even if I live in a country where it rains constantly.

I'll keep on using and paying for Kagi, I really like what they are doing so far.

Yeah, their product is too good to cancel unfortunately. But the fact that they don't seem to care about search any more, instead focusing on AI and browser stuff, is disappointing.

pathetic

Yep. I canceled the two accounts I’m responsible for.

I thought Kagi was going to be search for adults, but they have a serious problem with chasing the latest shiny API.

They keep jacking up their cost per search for features I actively dislike. I hope another paid search engine arises.

Bing increased their search API from 1.25 cents to 2.8 cents. As they are a wrapper around Bing it makes sense they have to increase their prices quite a bit.

LOL they’re just a wrapper around Bing??

No but they do incorporate Google and Bing results in their search. They should probably work towards their own index to lower their costs.

Yeah, ultimately this is what turned me off. Used the beta and loved it for as long as it lasted. When it ended it was hard to migrate elsewhere but I couldn't convince myself it was a good idea to continue investing in a service that was entirely at the mercy of its direct competitors and shows no signs its working to reduce that risk and cost.

Unless they mitigate those risks they will only exist for as long as google or bing wants them to. The only ways they survive are: - Mitigating those risks and costs (e.g., building/using own index, well designed caching could help) - Staying small enough in terms of searches and users to be under the radar for Google and Microsoft - Pray for the mercy of two of the most ruthlessly anticompetitive companies in existence (laughable) - Convincing Google or Microsoft that they are worthwhile to acquire (but this kills the service for me anyways)

Price hiking +150% for the stated reason that my direct competitor increased my costs certainly shows the pressure is on and working as intended. On the off chance that kagi devs or management reads this, PLEASE find a way to isolate yourself from being totally reliant on google,bing,etc. Unless you are going for an acquisition exit from Google or Microsoft, it will kill your company eventually.

They have their own index[1]. It's not easy, when a bunch of sites block anyone who isn't Google or Bing. But this is the same strategy Brave seems to be pursuing, where they try to rely more and more on their own indices.

[1] http://teclis.com

Good to know they are working on this.

Is there a legal issue with spoofing user agent to be the google crawler? Spoofing is certainly enough to get rid of article paywalls for 99% of sites Ive encountered. At least last I heard you can also work around cloudflare captcha by just routing requests through a worker on their service.

> The crawler is hybrid, using async python requests and puppeteer with uBlock Origin. The way detection works is we count the number of uBO blocked requests on the page, and if too many (threshold is set to 5), we kick it out, leaving only "clean" pages in the index.

Fascinating; cnn.com reports 47 on the front page, npr.org is at 16, developer.hashicorp.com is at 9. I don't think that metric is doing what they think it is, or rather maybe they're trying to target only savanna.gnu.org style sites or something

Same here. I Would have appreciate them to keep price for early adopters. It would have been a smart move towards dedicated users/believers and prevent them from the unavoidable bleeding to come... that will lead to more money issues. Too bad, I absolutely loved it.

It seems to be the case, though: "Every account with an active subscription at the moment of the pricing change on March 15 will get the “Early adopter” status. This will make the special “Early Adopter Professional” plan available to them instead of the regular Professional plan, with the main difference being 1,000 free included searches monthly, instead of 700." Ref. https://blog.kagi.com/update-kagi-search-pricing#existing

Back in September they promised this[1]:

> If such change to Individual plans is to occur, we plan to grandfather-in all early adopters (meaning all current and future paid customers, up until this change) allowing them to keep their existing subscription price as long as they don’t cancel it.

My guess is that they will focus on the "subscription _price_" wording. Technically the price didn't change, since you can still pay them $10. They "just" changed the terms.

[1] https://blog.kagi.com/status-update-first-three-months#futur...

It's unfortunate since this is not what I (most people?) think when we hear "grandfathering".

Also, why do we find this out over a blogpost. Where's the email saying "oh by the way the your subscription is changing in a drastic way"?

They sent out an email last night, to me at least

Huh, must be just me. Mine doesn't seem to be anywhere, I have the product email setting turned on, and I get their billing emails. Strange.

Mine was in spam with a pretty high spam score.

Same here, I immediately canceled upon reading about the changes.

Same sentiment here. The last thing I want to do is adding friction to my research and having to consider whether I should use Google instead for some queries.

So under the new plan, I'd have to base my decision on the ultimate plan, $25. That's quite a steep change from $10...

I'll probably get the annual plan to lock it for a year and evaluate again next year.

The most annoying part is that it seems that the price is increasing partly due to their investment to AI and the browser. They are cool and all but I only agreed to pay for search :/

I'm afraid idea of paying for search engine has no future at all. Connecting my search queries with credit card is no option for anyone who want privacy - no matter what Vlad saying or not.

Without any proof there could be only trust.

Kagi is a bit of a HN darling so I know I'm putting my neck out here, but even after trying the trial, I'm not sure what the value prop is.

I would happily pay for a search engine that provided good results, but seeing as it's ostensibly Just Bing under the hood, I'm not sure what I get that I'm not getting from DDG or MetaGer + an ad blocker.

Kagi doesn't strike me as a privacy alternative given that all my searches are necessarily tied to a user id which is further tied to a payment method.

Finally, the metered usage feels far too much like an ancient cell phone plan. I really hate the idea of me paying for search only to have to switch to actual Bing when I hit some limit.

I like what Kagi is trying to do, but I don't see it as either sustainable or awfully useful unless such a service owns its index.

Feel free to let me know what I missed, I'm sure Kagi's paying customers are paying for a reason!

I’m a paying customer.

I pay mainly as an experiment to figure out what my searches actually cost.

If those costs are covered by advertisers that I block, my free search experience is paid for by people who don’t block those ads. I don’t like that thought.

I may go back to DDG if the new payment structure is insufficient (I don’t know if I search more than 1.000 times a month). But it is somewhat eye-opening how much I take search for granted.

If you click into your kagi billing, there is a usage dashboard.

I thought I'd be fine with the 700 searches a month.. but my average is 1600.

$300/year for a search engine is probably more than I am willing to pay, especially for an individual subscription.

I used to use DDG, but the search results were so bad that I had to !g all the time. With Kagi, the results (which are mixed from various services, not just Bing) are actively superior to Google (so much less spam!) almost all the time, and the only Google search service I still use regularly is Maps.

That said, while I've been happily paying $10/mo for the pro plan for a while, I'm not convinced the 1000 searches/mo will suffice. Guess I'll find out soon enough.

Update: I checked https://kagi.com/settings?p=consumption and to my surprise I'm averaging under 20 searches a day total, even though Kagi is my main search engine on both mobile and desktop. So looks like I'll be OK after all.

Sadly, for programming, I've had to use Google quite a few times lately.

Their raise feature is nice, but always finding stack overflow (because I raised it) on top of ACTUAL documentation for a specific topic kinda ruins it.

>Their raise feature is nice, but always finding stack overflow (because I raised it) on top of ACTUAL documentation for a specific topic kinda ruins it.

So you changed the results, and now you are complaining because the results are changed? I don't get it.

I think it makes sense. They boosted stack overflow because they think it's often relevant, but not necessarily always the best resource. But now it's always #1 when oftentimes there is a clearly better resource. They just wanted it to be #2 instead of #10.

Basically they are wishing the boost feature had room for more nuance.

There is a bit more room for nuance, you can pin domains, which places them above "raised" domains. I've pinned MDN and official documentation sources, raised StackOverflow and blocked SO clones. It works well for me but YMMV.

Thanks for providing the link.

I used 517 searches in February.

For March I look to be using 700 searches.

Seems like the pro plan will be sufficient for me.

Flip side, it's not uncommon for me to do 200+ searches a day. My lowest month was 900 searches but I went over 1800 frequently. Not worth $25/m for me personally at that point. I was sold on the idea of being grandfathered in at $10/m...

You can still be grandfathered into unlimited, for the next year anyway.

I just updated my monthly subscription to annual for just that purpose.

For the past 4-5 months I've kept three browser profiles, which I use simultaneously to compartmentalize things across work/personal/hobbies and to try out different browsers and search engines. I use Kagi on two of them and Brave Search on the other (I gave up on DDG as it disappointed me too often; Brave seems slightly better than vanilla Bing as they combine it with their own index).

The difference in results quality is stark. On Kagi I have to !g maybe once every few days, and usually I don't find what I'm looking for on Google either, but on Brave it feels like I do it for a third of my searches, often for ones where I actually know exactly which result I want and am using the search engine as a shortcut. So whatever Kagi is doing, it's definitely not "Just Bing".

From their Discord, it is apparently some combination of Bing+Google+their own small index, which makes sense because for niche searches where Bing and Brave completely fail, Kagi's results seem to closely mirror Google's, with the benefit of its result boosting and filtering features. For more common searches it seems to match or surpass Google regularly.

I've just switched to the annual plan to lock in my current $10 unlimited searches rate, and will re-evaluate after a year. I can't justify $25 a month, but looking at my history (and guessing how much I'd need if I moved all of my Brave searches to Kagi) I may not actually need more than 1000 included + 200-500 pay-as-you-go searches per month, which is juuuust on the boundary of what I'd be willing to pay.

I was curious how much/if any unique index Kagi maintained because I also finally gave up on DDG as its repackaging of Bing became worse and worse to the point where there was no value add vs just going back to Google.

But now I’m even more hesitant on Kagi since I knew it used bing, whose results both direct and from ddg have been supremely disappointing, but it also pulls google which…I can just get direct from the horse’s mouth? So the value add seems to be whatever is in their small index. Hmm I just dunno.

> I'm sure Kagi's paying customers are paying for a reason

No ads, blazing fast, and the search results are more than adequate for me (I don't find myself ever reaching for Google as I did with DDG). I'm not too bothered where the results come from when those three things come together. It's just the premium search experience I want.

> all my searches are necessarily tied to a user id

I know that theoretically Kagi could sell me up a river at some point in the future. However, they have every incentive not to - they'll see a huge exodus of users if they ever do that - so the alignment of incentives feels right here.

For the moment I feel reasonably confident that my search preferences aren't being sold to the highest bidder (or every goddamn bidder). If that ever changes, I'll reconsider.

Overall I feel more comfortable paying for my search, and I want to support this business model.

> the metered usage feels far too much like an ancient cell phone plan

I'm going to wait and see how this works out for me. If I find I'm exceeding the $10/mo plan by a lot I'll also have to reconsider. But because I'm partly here to support the business model of paid search, I'm willing to give Kagi some leeway to find a sustainable setup.

The alignment of incentives is not as tightly aligned as I'd like. Because Kagi has this data, they could be bought out by another company and release blog posts about how this merger is actually a harmonious union of privacy. A sinking ship with the livelihoods of many families on the line can easily convince leadership to sell. Having a distressed company bought out is not some special story, and things like this easily go on without many customers knowing. How many Tom Bihn customers know that the company has been bought by a VC?

On a mildly tangential note, the way their marketing language describes their new plans leaves a poor impression with me, saying that I get something for free if I pay for it. Did you know? If you buy a Twix for $2, the first bar is free.

Your concerns are valid indeed, and on top of them one must also think about what's the alternative. Because if you leave service A you'll necessarily use service B - I assume nobody leaves Kagi to give up searching. So the choice is between a possible bad outcome (Kagi) versus a known bad outcome (Google).

The difference in privacy I see between Kagi and Google is that Kagi requires me to have a signed-in account to search, and Kagi accurately associates more valuable information with a signed-in account.

I don’t think you can have both ad-free (e.g. paid) search and anonymous search at the same time.

You have to pick one. And you can’t really fault Kagi for providing the one when the other is already “adequately” covered by Google.

cryptocurrency?

Interesting point.

Maybe Kagi could offer a more privacy friendly "fill a wallet with crypto and we'll deduct a certain amount per search" option that doesnt require user billing data.

Im not a current user but would be more likely to test it if available.

Surely you can. You can use blind signatures, it's like issuing anonymous tokens in the style of David Chaum digital cash. Or you can just use existing cryptocurrency.

Supposedly they are not doing it because of advantages of associating your payment method and searches.

I don't know how Kagi internally operates but for billing purposes I imagine it would be enough to record that you searched. Not what you searched.

On your last point, you can check the usage statistics in your Kagi settings for the previous months. That way you can see if you would exceed the limits.

Apparently I search around 1k times per month, which means the new Professional plan wouldn’t fit my needs.

I decided to cancel my subscription, Kagi didn’t provide that much benefit over Google to me. I just needed this last push! I do think it’s a good idea, we definitely need more competition in this market.

> Kagi doesn't strike me as a privacy alternative given that all my searches are necessarily tied to a user id which is further tied to a payment method.

I agree to some extent, but also consider: if you are not paying for search, then they are going to have to monetize somehow, and the most likely way they'll do that is through selling search history/data.

The only way to be respected as a customer is to actually be a customer, and for that you have to pay. Presumably Kagi could start accepting anonymous payments, but your searches would still be tied to an account.

> the most likely way they'll do that is through selling search history/data

No? Google, the largest search engine, doesn't monetize by selling search history/data. I would hazard a guess that not a single free search engine monetizes by selling search history/data.

Selling ads is extremely and literally different from selling search history/data.

> Google, the largest search engine, doesn't monetize by selling search history/data.

Google, the owner of the largest ad network in the world, does not make money from your searches? Are you trolling or completely misinformed?

Google indeed does not sell your search history to third parties. They make money by letting third parties target ads to you with it.

I think they are being pedantic. The point they are making is that Google does not sell your search data directly, rather it sells ads that are optimized thanks to your search data.

IMO it's a moot point.

Paying customer since last year. Kagi's results are okay or really good depending on what I'm searching. After around 1 month of experimenting, I blacklisted/boosted several domains on Kagi. After that, I never had the need to go to DDG or bing anymore.

That being said, I think Kagi being a search engine itself AND basing their statistics for pricing on Google and DDG is a horrible move...

Those are my exact feelings since testing Kagi. I did not found it appealing as a plain search engine, nor private.

But they have recently shown a tech preview of an "Universal Summarizer"[1] which I have found far superior to ChatGPT (cGPT is worse than some freely available pre-trained models in this regard).

I have asked Kagi and cGPT to summarize my own post[2] which Kagi did rather well (I don't have a screenshot), while cGPT spilled utter nonsense[3], mentioning hardware and software that isn't mentioned in the post and which - in some cases - I have never used.

While Kagi is unappealing to me at the moment, I will happily try it out the future again.

tl;dr: I wrote about using: FreeBSD, Linux, Fail2ban, blacklistd, Terraform, Ansible, Postfix, Dovecot, Kubernetes, Jenkins, ArgoCD, Git and nginx.

ChatGPT stated that I wrote about MacBook Pro, iPhone, AirPods, Kindle, Chrome, iTerm2, VSCode, Vimium, Adblock Plus, Dropbox, 1Password, Trello and Slack.

[1] https://labs.kagi.com/ai/sum

[2] https://wojteksychut.com/posts/work-tech-i-use-privately/

[3] https://wojteksychut.com/pic/chatgpt_post_summarization.png

> I have asked Kagi and cGPT to summarize my own post which Kagi did rather well (I don't have a screenshot), while cGPT spilled utter nonsense

> https://wojteksychut.com/pic/chatgpt_post_summarization.png

ChatGPT currently has no capability to access external sources, and its training data cuts off at the end of 2021, so there's no way for it to have ever succeeded at this task. It was essentially asked to summarize an article it has never seen, so it hallucinated the entire summary based off of the words in the URL as that is the only information the model was provided. For a more equivalent comparison you'd need to copy the text of the article into the chat input.

Of course that doesn't change the fact that it responded to your query with totally fabricated nonsense, which is a horrible failure mode that points to why it can be so hard to trust LLMs' responses, but I do believe the disclaimer popup that appears when you launch ChatGPT notes this particular limitation.

It spelled my last name correctly in 4th paragraph (although could have got it from domain name). This domain was registered in 2023 so it could not have data from 2021; but maybe has been fed from Bing later?

It currently states: "As an AI language model, I don't have direct access to real-world events that have occurred after my knowledge cutoff date of September 2021. However, I can access information and data from websites created after September 2021, as long as they are publicly available on the internet."

> it responded to your query with totally fabricated nonsense, which is a horrible failure mode

Agree. I would be fine with getting "I cannot summarize this post as I don't crawl external sources" but not this.

I pay because their results are as good as or better than Google, and because they aren't in the business of marketing to me or selling my personal information. That's it.

All this crap with AI and Kagi releasing a browser is a distraction from that.

I've found being able to change the weight of different origins in search is super powerful over time. I've filtered out most of the SEO spam and low-quality websites that plague my searches in other engines at this point, Kagi doesn't serve them to me. I've also pinned high quality resources like MDN so it always shows up at the top of the list if it has relevant content.

Kagi saves my time and gets me to better results faster. At least for now, my time is worth more than Kagi charges. As long as the math keeps working out that way, I'll continue paying for Kagi.

The pricing changes are unfortunate, yes, since they encourage me to think about querying, which ought to not be the case.

The more worrying update here is that Kagi is not grandfathering in legacy plans beyond the next billing cycle, which is a departure from a promise:

Kagi's claim to privacy is intrinsically tied to their capacity to keep their word. If they say one thing and do another with pricing, how can I trust they'll do what they say when it comes to privacy?

I paid for Kagi the first moment I was allowed to, and this news soured me on Kagi overnight. Trust is hard to earn back.

I jumped on Kagi with multiple family members due to their grandfather promise. The lie hurts all the more because they aren’t a big company. If they’re already “altering the deal”, what will they do when they’re big?

Agreed on both accounts. As someone who is not even a heavy user - I have over $50 in "surplus" right now, meaning they're making money off of me - I am likely to cancel for both of these exact reasons despite the fact that the actual charge to my credit card would not change next month (and I could even cut my cost in half if I wanted to).

Agreed. I also don’t like how they are jumping on the AI bandwagon and splitting their efforts between search, a pointless new browser, and AI. It’s like Google all over again.

I’m happy to give them $10 or $25 per month for excellent search and privacy. But I’m really not interested in funding their other junk.

An important tidbit from their Discord. The AI is just the commercial one from OpenAI. Paying $5 per 50 search summaries for it according to the founder of Kagi.[1] It is not in-house.

1: https://media.discordapp.net/attachments/925992877602000967/... (Backup: https://imgur.com/McoRELC )

Sorry for the value statement

But good lord, that's such a dumb, dumb, dumb decision to integrate this thing onto Kagi then

I'll keep my subscription on the 10usd one, but yeah this drops my interest on the company precipitously and rather than just recommend it, I will just not, or do it with a warning that the roi of subscribing is only so-so

Everyone is entitled to their opinion but I thought that their summarizer tool was amazing. I was using it multiple times a day to get summaries of long articles and pdfs.

They have updated the FAQ section of the announcement to directly address this (very, very valid) point:

> Q. Didn’t you say in September that current subscibers will be grandfathered in?

> A. Yes we did say that in September. We are sorry that we have to walk back on that promise and we should have done a better job at communicating the pricing change debate that has been going on for over three months with our community.

> A lot of things changed in the meantime that we could not anticipate and predict, namely increase in search costs and popularization of generative AI which further increases the cost and making us lose even more money per user than before. That is not sustainable for a bootstrapped startup and we had to make the next best decision.

> The decisions made (the price change and cancellation of grandfathering) is exactly the necessary step to keep us in the business of search, aligning incentives between us and users, and keeping the best interest of our users in mind.

> We did the best we can, and we will still going to grandfather in everyone for up to a year on the old plan, and then on a special plan after that indefinitely (which still loses us money, just less). Discussion about this was long and hard and we made the best possible decision given our abilities and the circumstances.

This is so incredibly disappointing and basically confirms that we're (at least in part) paying for their AI experiments - something that I personally am not at all interested in.

There was a thread here [0] a month ago about the AI stuff at Kagi, my take was commenters were overall enthusiastic about it. At the time I said I wouldn't pay for it [1] and got a bunch of replies telling me how valuable it was.

I really want Kagi to succeed, I've been following the results of the pricing change closely because it seems like it's not going well and I don't want them to go out of business. I hope it will convince them to drop the AI stuff, or at least confirm that there's strong evidence it will pay off somehow, not just the hype that makes everybody fawn over llm stuff.

[0] https://news.ycombinator.com/item?id=34646389

[1] https://news.ycombinator.com/item?id=34647775

> I paid for Kagi the first moment I was allowed to, and this news soured me on Kagi overnight. Trust is hard to earn back.

Me too. I still have many months of my early-adopter $10 unlimited annual subscription left. I'm going to start drafting my migration plan several months later. I no longer trust them, nor do I want to do business with them anymore.

There's the Bing API price thing yeah. But it's also clear that they're trying to fund their AI experiments. I'm a paid user of OpenAI's GPT-3 API and ChatGPT plus. I routinely ask the GPT family to imagine things for me. But I don't want my search engine to imagine things, even if they're based on search results.

I speculate Kagi knew their target audience won't be happy about paying them for AI things, so they just came up with the whole average monthly search things as a cover...

I'm a happy Kagi customer, but going from $10/mo to $25/mo seems like a very steep increase. (I realize that much of it is probably driven by Bing more than doubling the price for their API results.)

One thing that feels kind of disingenuous to me is the number of searches that "a normal user" does in a month. The blog post mentions it several times, but they always reference numbers provided by Google or DDG. I have a feeling that the numbers for their "tech-savvy and heavy users of search" are _way_ higher than the averages of Google and DDG.

At my current usage, I would have to go with the $25/mo plan once my current subscription is up.

Tiny copywriting nit in case anyone from Kagi is here:

> The new Standard plan pricing will be $5/month, with 200 free searches included.

They’re not free; they’re $5/month. I know it sounds pedantic but on first read I thought, ok, so 200 free searches in addition to whatever you get for $5, which is… what? It makes it feel more complex than it is.

They are "free" in the sense that any searches beyond the first 200 cost extra. They should have just said that searches beyond 200 per month cost extra.

I found that part confusing. It sounds like they tried to use some non-standard language to sugarcoat a change they expect users to dislike.

They do have team plans where each user is ~20 USD with no included searches.

A few things rub me the wrong way about this article:

- I didn’t receive an email clearly indicating the pricing changes and pointing to this article. Instead, I found it on hacker news.

- Every paid tier refers to the number of searches it allows as “free” despite requiring payment.

- The wording around existing customers led to me believing that the pricing won’t change until cancelling the current plan (grandfathering). However, once I came to these comments I learned that pricing goes away at the end of the billing cycle and will be switched to a new plan.

- Their words about average internet users’ number of searches feel so disconnected from who their actual users are and is incorrectly framing the conversation. If their goal is to truly expand to being the search that everyone uses, requiring payment will never allow that to happen.

I wish they had invested in building their own crawlers rather than AI and their Kagi browser.

Crawlers over ai would be nice indeed.

Simple math. It's worth it for me. I realise it's possible not many others feel the same, but even if Kagi quintupled their current prices I would still pay for it without batting an eye.

Why? Because of the time and effort it saves me.

I make around 1500 searches per month. If it saves me 3s per search (I'm 100% convinced it's actually way more), that's saving me 75min in a month. I'm paid more than the unlimited plan per hour.

But it's hard to put a number on how much it's worth having a search tool that is algorithmically unbiased (except against ads), that actually works, and that denies big tech my data.

It is true, though, that they went back on their promise to grandfather current customers. That will stay in my memory.

> algorithmically unbiased

They’re adding AI, where the human biases come baked in, and charging us extra for the insult.

It is sad that you are being downvoted. The comments are generally the tipical knee jerk rage reaction HN has after they decided to feel "betrayed" by a company, and yours is one of the few not following the groupthink.

I dont have anything for or against Kagi, I dont use them and don't care for them. But I see no reason to downvote your comment.

> knee jerk rage reaction

I’m not sure I’d call it a “rage reaction” to object to a 250% price increase. None of the top comments could by any stretch be described as “rage”. If you have to exaggerate to make a point you should always ask why.

You'd think that HN of all places would understand that a startup doesn't get pricing right on the first try.

> It used to be 1.25 cents per search. Microsoft recently increased Bing search results API cost to 2.8 cents per search

I guess Microsoft decided to switch their strategy from "help startups take market share from Google" to "kill the competition and try to get users to search on Bing"?

Grandfathered subscriptions will receive 1000 free searches instead of 700, so I'm unaffected by this change.

But it sours me how much money they need to throw at this. They are too dependent on external services.

In my searches, nearly all results come from external indexes. Either they can't or they don't want to improve their own crawlers. Before increasing the prices, they considered disabling their most expensive search provider (I'm guessing it's Google) with catastrophic results on search quality.

I was hoping that AI would level the playing field against their big competitors, but looking at their pricing chart, that won't happen either. Summarizing an article can cost up to three cents per question.

I will stick around, but I don't have much hope that this business model is scalable.

> Q. Where does the search usage data (99% of users search less than 200 times a month) come from? A. The average person searches Google three or four times per day. (90-120 times per month)(...) According to DuckDuckGo’s data, the monthly average is about 30 searches per person or one per day.

The average does not imply anything about a distribution, and the links provided do not back up this claim at all. Furthermore, Kagi's target audience is not composed of average users. I find it quite misleading because Kagi could provide data from its own user base to answer this question.

I am a Kagi subscriber and I like it a lot, but I will probably cancel after the current month. 1000 searches per month is probably enough for me, but I hate services that change the model and pricing all the time. It's just not for me. Also, I don't really care for the AI integration. I wish they'd just have kept the unlimited searches for 10 per month plan (which I don't use up anyway, so they'd make a nice profit on me) without the AI stuff.

These changes also make Kagi a touch sell for friends and family. Most of them would probably do such a small number of searches that they'd be a large net profit, but the idea of having only a limited number of searches would be too off-putting for most.

> I hate services that change the model and pricing all the time

It's hardly "all the time"; this is their first pricing change, no? I was a part of the free private beta, and then started paying when they started charging, and I don't recall any changes until now.

It seems unsurprising that a paid search company (something that is pretty new, business-model-wise), might not get their pricing correct the first time.

In September they said:

If such change to Individual plans is to occur, we plan to grandfather-in all early adopters (meaning all current and future paid customers, up until this change) allowing them to keep their existing subscription price as long as they don’t cancel it.

https://blog.kagi.com/status-update-first-three-months#futur...

So they changed the pricing terms.

Also, they broke their promise from last year, saying that they'd grandfather-in all early adopters, as long as they don't cancel:

https://blog.kagi.com/status-update-first-three-months#futur...

Now they changed it to only the current billing period.

Exactly. That exact statement encouraged me to subscribe. This change is disappointing.

Same. I haven't used Kagi that much yet. But one of the reasons of subscribing was to opt in to the then-current terms.

Oh. I didn't realize that they would not be grandfathering-in existing users until I read your comment, believing their earlier statements. Confirmation bias is a hell of a drug, but it made sense after I read it again. Thanks for that.

> Every existing subscriber will have their current subscription honored until expiration. That means if you are a subscriber at the time of the new plan rollout, you will still get unlimited searches as a part of your original plan until your existing subscription expires or is set to renew.

Their $5 plan makes no sense.

They're charging 0.015 per search when you're "over limit" but 200 searches would be $3 on "pay as you go" after your plan runs out, which is better than the bundled 200 for $5.

The $10 plan is only marginally better, 700 searches (cost $10.50 PAYG) for $10.

Right, and there's a big middle ground where it doesn't make sense to upgrade to the $10 plan, even if you go over the limit of the $5 plan. I checked my usage, and it looks like at most I do around 350 searches a month. That would cost me $7.25 ($5 + 150*$0.015).

It's not surprising to me that the more expensive plan is a "better deal" than the cheaper plan. But it's just weird to me that you'd have to get to 534 searches before the $10 plan makes sense, and the $10 plan only gives you another 166 searches to work with.

If the subscription price is not zero, the included searches are not free. In this regard, the wording of the pricing page mockup and this blog post is dishonest - or at the very least inaccurate.

Not a fan of the changes otherwise. I average around 1200 searches per month which would require me to get the unlimited plan. $120/year was already a steep price compared to my other yearly subscription costs:

- VPN: §50

- Broadband internet: $230

- Mobile subscription: $290

Not willing to pay more to Kagi than to my ISP and not willing to use more than one search engine.

Not a fan of the changes otherwise. I average around 1100 searches per month which would require me to get the unlimited plan.

I don't like the changes either, but I don't think this is true. You could get the 1000 searches plan for $10 and then pay-per-search the additional 100 searches.

Fair, thank you for pointing that out. The idea of paying per query for a search engine seems so alien to me that I just skipped over this option.

Yes, it's really weird, and I think they're going to lose a lot of customers who have the same first impression as you, that they'll have to bump up to the too-expensive plan because they're a small amount over the limit on the cheaper plan.

> The idea of paying per query for a search engine seems so alien to me

That’s odd. It seems like the most natural thing ever to me.

You need a paid subscription and additionally each search costs money (except the unlimited subscription)

You get X free searches per month.

It doesn't seem dishonest or inaccurate to me at all.

If I pay $10/month for 700 searches then the price for these 700 searches is $10/month, they are not free. The price per query for the additional searches is just higher.

It's not free if you pay for it.

I was a paying kagi subscriber for about 5-6 months before canceling my subscription. Before that I participated in the beta, and was very excited in Kagi's mission. The service did provide better search results for me than google or bing, partly due to no ads and my ability to better filter out blog spam. I legitimately enjoyed using the service, but in the end could not rationalize paying $120 a year for search. That's more than I pay all in for email, VPN, online storage, password manager, etc.

I was really hoping they'd work on their own indexing and decreasing their costs. For simple, good, reliable, no advertising search I'd happily pay $5-7.50 for. I recently had a thought about re-subscribing when I got this email last night, and this pricing model is not appetizing at all. Not a fan of metering or search limits, I tried using their free plan but having to spend even a .25 of second to think if I want to use up 1 of my valuable search credits ruins the whole experience for me. In the 6 months since I unsubscribed their pricing has gone up and they are tacking on AI which they are just leveraging openai for?

I'm disappointed to say the least.

(subscriber for the past 8 months, planning to convert to annual to lock in $10/mo for the next year and reassess then)

The AI tools they have been releasing are interesting, but Kagi desperately needs to decrease their average cost-per-search so that they can offer more realistic numbers of queries per month at a $10 price point.

I'm not sure what the solution is - maybe generating smaller indices for particular verticals? For some classes of question (for example looking up documentation) I would expect there are a surprisingly small number of sites that consistently end up as top 3 results, and everything else can be put behind a 'load more' button that queries the paid APIs.

(The problem then becomes identifying when this is the case)

While it wouldn't 'fix' the cost of long tail searches, identifying 'easy' searches and answering them directly might help - looking at my own search history, I'd say maybe 1 in 3 of my queries would fall under this category.

I'll also convert to annual to get unlimited searches for a year. The search engine market is moving so fast now anyway that things may be well different a year from now.

The core of a search product is that I want to be able to search. I don't want AI. I don't want a web browser that only works on Mac. I don't want metered searches.

I wouldn't mind spending more money if it helped them develop their own scraping and be a viable alternative to Google in the future. But there's no indication they are making the business choices necessary to do that.

Additionally, they said they would grandfather in old users, which they did not.

I'd been subscribed for a while, but I just canceled my subscription. So disappointed.

Here are my search counts and costs to Kagi for the recent months as a student, mostly traveling in Feb.

Feb 2023 1253 $15.66 Jan 2023 1612 $20.15 Dec 2022 1390 $17.38

Bummed by this change, I guess I'll snag the yearly plan now and see were we are 12 months from now. I don't know if kagis results are better but the experience is so much better for me and I love being able to prioritize sites I care about in results.

I don’t understand how they think 1000 searches per month is enough for a family. Also the cost of additional searches makes it a non starter for my family.

Looks like pay per view has finally come to web searches as well.

I understand that they may need to adjust prices, but having a search limit just feels ... bad. Imaging being on the go, trying to look something up quickly, only to be presented with the message

> Search limit reached.

That's not how it works. If you go over the limit you pay per search. Not totally sure that's better but still :P

Actually, that is how it works if you use the Pay-per-use Limit.

The most disappointing part for me is that they didn’t keep the promise of grandfathering plans. I’ve lost confidence in them and will most likely cancel my subscription. Luckily search is mostly fungible.

I checked my usage and tend to use ~1200 searches per month. Kagi shows that of the money I spend, around 60% pays for my results, so it seems like Kagi is still profitable with the current pricing.

Presumably though, they don't see this as sustainable. I wonder why? What kind of margin are they looking for here?

I think those costs take into account external API prices but not internal ones (such as employees, servers).

Moreover Bing increases pricing in May for their API and I guess they are trying to factor that in as well

Bing pricing is more than doubling, so they'll be losing money on simply proxying your search requests, let alone everything else they do.

Really disappointed with this pricing. Such pricing will kill their product and move regular consumers away from the product.

I have used Brave search that gives similar search results for way less money.

And that's really the sad thing. If this pricing is too high for the business to be viable, it suggests that people would rather participate in surveillance capitalism than pay for privacy.

I think that's been clear since at least the early 2000s

Not really fair. I think one could argue that people don't really realise the extent and impact of surveillance capitalism.

My experience is that once people do find out, they continue regardless.

Please explain how connecting my search queries with credit card makes me nonparticipant in surveillance capitalism?

Yikes, I understand why they're doing this, but I just learned I do about 1500 searches a month, and I'd have to upgrade to the $25/mo plan, which is a pretty steep increase. And I don't care about AI.

I will probably move back to Brave Search.

I've been quite happy with Kagi, but I do a lot of searches throughout the day, far more than the "700 free searches per month" they offer. (Usage tells me I'm using around 1500-2000+ searches per month.)

I've been on the USD10 pricing for a long time. Now it's soon to be USD25 per month for my kind of tier - which seems crazy steep, and more profiteering than an attempt to bring search to everyone.

I am a happy user but just checked my usage and I'll need the 25$ package - which I think is too much for search. I'm cancelling unfortunately.

If you switch to annual billing now then you'll get a year of the old rates for $120. That's what I just did.

That makes sense if you are confident that they will still be in business 12 months from now. In light of these changes, and the number of people saying they will cancel, I don't share that confidence.

I for one don't mind too much this new pricing. I'm not ready to spend $10/mo in a search engine subscription, but $5/mo hits the spot for me. The only thing I'm not sure is if 200 searches per month is enough, I have no idea how many searches I do but 200 sounds pretty low. 1 search often ends up being 10 searches when you need to tweak the keywords or the quotes.

I only use about 350-450 searches a month at present, so this pricing change won't affect me. However, I've not been crazy about Kagi's search quality lately, and I'm not convinced that more deeply integrating AI into the results will solve that. I'd rather the roughly 55% of my unused subscription went to improving the core product, but I'm not going to cancel yet because Kagi still provides the value of being comparatively confidential with my data.

(When it is revealed — as the narrative of this story demands it must be — that they sell you to advertisers like everybody else, I won't be surprised but I will be disappointed)

Every search engine seems to be scrambling to throw AI at their product: is it because they've thoroughly tested it, and it definitely improves the results? Or is it because it's a bullet point in the feature list? Feels like there is potential, but it also feels like a gold rush too, so I'm sort of waiting skeptically to see how it will shake out.

With 1k-2k searches a month, $10 seemed reasonable. However, $25 does not - it's far too much of a price increase. Most people here can already get same quality results from google with an ad blocker. I get that the service costs money, but for an end user, it's not really justifiable.

Sadly, I feel the same way. With prices going up everywhere, I have to cut some subscriptions, and Kagi will be one with this change.

I tried it out today for a full day to see whether I should quickly subscribe to get the legacy professional benefits. I found having a limit on the number of allowed searches really uncomfortable. So it is a nope for me at this price.

Also, the search engine market is really heating up. We have - Bing with a GPT chatbot - Brave Search with lenses, similar to Kagi - DuckDuckGo with a limited chatbot - Swurl is cool as well (but I think that is just a frontend for Google)

...and they are all free to use. I am not sure if Kagi will survive another year with this business model. IMO, they should focus on freeing themselves from Bing's API and build their own indexes to drive down costs, and also drop anything AI related gimmick, and embrace the UNIX philosophy: do one ting well.

I wish there was a cheaper option without the AI feature (that is probably what costs them the most).

That's what I thought, too, but from the blog post it feels like AI searches will "cost" a variable amount of requests. So maybe the price increase is unrelated to AI, but they market AI because people apparently love that?

Not sure, and same as you: I don't want generative AI and I don't want to pay for it. I wish they made it clear that I won't have to.

Also I don't want to pay for their browser that I don't use. Really I'm interested in paying the true price for my searches (instead of being tracked for ads).

I just read the update and my first reaction is that the pricing structure seems fairly complicated.

Enthusiastic paying Kagi user here and I felt the same. What helped is to find the "Usage" section of my account (under the Billing section) to see how many searches I've been doing in past months. In March, so far, I've done 180. I wonder if they count "!g" searches? I don't use this often, but I'm curious.

We are all waking up to realize what it takes to run a profitable search company without ads and surveillance capitalism. I am genuinely happy with Kagi's service, but I am confident that less-technical users would rather just keep using "free" search like Google, Bing, etc. The vast majority of users just don't know or care about privacy, and even if they do, the vast majority of people in the world aren't going to pay for search!

I read in the FAQ that "bang" searches (e.g. !g) don't count towards usage.

I'm switching my monthly plan to annual today.

My read of the announcment is that this will grandfather me into unlimited search for the year, while excluding me from any of the new AI enhancments.

I hope this clearly conveys my opinion on this change to whomever is bean counting :)

I just cancelled my plan. I found myself quoting every single keyword over the last month ala google and now the price increase?

You gotta be kidding. No one asked you for your new costly features btw.

People wanted a decent search engine, not a Swiss army knife.

Not sure why they have so many tiers. After all, they have per search pricing once you hit a limit anyways. Quite confusing.

I personally don't care about AI generated summaries or anything else that 'enhances the search experience'; can I get a plan that doesn't use those flows and saves you money?

All I ever wanted was to quickly find the source for a tidbit of information I know exists somewhere; I'll draw my own conclusions based on the source

The only reason I switched from Google was because Kagi presented me with what I wanted on page one vs. having to waste time navigating to page two or three of Google results

But over the past few weeks, the blogspam is back, and my reporting seems to do nothing...

What I don't understand is this idea that searches cost them 1.2 cents each. 1.2 cents is the cost of operating a 4-core, 16-gig, 5-gigabit server on AWS for nearly 5 minutes. If a single search cost Google 1.2 cents, Google would be paying $44 million a day to cover it. I cannot make that math work, and it makes me reticent to believe them and continue paying.

Only thing I can think of, is that they have divided their entire operating costs by number of searches a day, and 1.2 cents is not really the marginal cost of a new search, which is _super_ dishonest.

It's Bing API usage cost as they mentioned, and Bing hiked the prices up 100%, as they mentioned.

Most of their searches are combining data from Bing, Google and other sources.

They never stated that this cost is their infrastructure cost.

> If a single search cost Google 1.2 cents, Google would be paying $44 million a day to cover it. I cannot make that math work, and it makes me reticent to believe them and continue paying.

You don't believe that Google is spending at least $44 million a day on providing search?

The more disappointing part for me is that they didn’t keep the promise of grandfathering plans. I’ve lost confidence in them and will most likely cancel my subscription. Luckily search is mostly fungible.

Too bad they decided to become irrelevant. Kagi was a fresh breeze and liked it very much, but by abolishing the free plan (which is now a merely short trial) and rising the prices this steeply will hurt them.

It's so much eyebrow-raising, too! All I wanted is a good search, but now they try to justify by saying "oh no our shiny AI costs so much!" – a feature I did not want and neither intend to use! Same with their browser? Why is everybody so fixated in making their own?

It is maddening. I recommended Kagi to all my colleagues and friends. Will stop doing that.

So does Kagi put a date on _every_ search result ala Google? One of the reasons I finally drifted away from DDG was its very spotty displaying of the age of each result. Was constantly ending up in far outdated articles

Ex searched DDG just now for “camp fire 2018” and only 1 of 10 results is dated. A lot happens in 5 years with lawsuits etc, I don’t want articles with updates from 2019!

https://duckduckgo.com/?q=camp+fire+2018

I checked, about half of the search results for that query are dated.

I’ve been a huge advocate of Kagi. The $10 was a lot actually but I was willing to do it. $25, no.

I've been a happy user since December, but I knew this change would eventually come. On the existing $10 USD a month plan I've been scraping under the "break even" usage point and I've only used it on my personal devices/outside of work.

Still using google for my day job since I figure it would tip me way over the point where it would be sustainable. Sort of justified it to myself that it's technically "my employers" privacy since I'm googling things related to developing their product and nothing to do with me personally.

In saying that I thought/hoped they would put in a huge drive to try and minimize the cost of search over time, not just rely on bumping up end user pricing. I don't think I can justify the price of the unlimited plan, which is what I would need if I actually used it on all my devices. That would be $40 NZD a month! For context that's more then I pay for Netflix, Disney+ and Crunchyroll combined.

On 2nd march I did 105 searches and Kagi tells me it costed $1.31. I'm currently paying more than I search. Still, with the new model, I'd pay more. Guess I'll cancel my subscription, too.

The lenses are still garbage too, where "wiki.*" doesn't match "wiki.domain.tld".

Why do so many modern sites disable zoom in the browser? It's a real pain in the butt.

Does anyone know of a workaround?

Found it

Firefox for Android

Settings > Accessibility > Zoom on all websites

I'm definitely a part of the outliers in those statistics given my monthly use varies.. sometime 800, other times +1200 queries.

The pricing seems reasonable to me although I do not see myself paying 25 bucks for unlimited search. I'll probably stay on the 1000 queries and see where it takes me... The fact that you'll pay per queue once you hit the limit seems to have been missed by some in the thread...

You do not have to upgrade to $25 unless the cost of per queue ends up being more expensive than the tier.

Additionally you can set a soft and hard limit and although it's of course more expensive than the current unlimited plan, it's imo still better than the alternatives.

One thing is for sure, I can't go back to Google, DDG or bing, Kagi is just so much better.

I really wish they sent an email about it. In my account settings, the option "Receive Product Updates" is turned on and in my opinion updating pricing counts as a (huge) product update.

If I hadn't found this HN post, I wouldn't have been informed about any changes.

I just got the email regarding this, may take a bit I guess.

I got my email at 11:18 PM PST. Perhaps they have determined a more optimal time to send you the email so you’d be even less likely to read it than I.

I did receive an e-mail.

I've just got the email as well, so I guess they hadn't sent them all at once

And with that pricing model, I'm out. I do well over 700 searches a month usually and it's not worth $255 annually for me to pay for a search engine.

I've cross checked results when I got stuff I wasn't really expecting and it was nearly the same as google anyway.

If you are already a subscriber, you get 1000 searches when the changes kick in.

I bookmarked Kagi a while back and have been using it occasionally as a failover when other search engines fail me, wondering if it would be good enough to stick as a daily driver. So far it hasn't really stood out to me but has been decent enough to keep trying. Maybe the searches I have tried so far aren't areas that it excels at?

Whelp, after these account changes I won't find out. I absolutely don't want to have to think about metering my search queries per day and would bet that the vast majority of users feel the same.

Hopefully Kagi can figure out a way to control their costs better and/or figure out a more accessible revenue strategy. Avoiding piling on the latest AI hype would be a good start...

What a bait and switch. Didn’t see that one coming.

It was hinted at for a few months on the kagi discord. People could even vote for different pricing models.

Most people who pay for a search engine don’t participate in chat rooms discussing their paid search engine pricing.

This will blindside Kagi if they’ve been relying on true believers in Discord for their feedback.

> It was hinted at for a few months on the kagi discord. People could even vote for different pricing models.

The Discord doomers are the ones pushing for AI in search to compete and price match ChatGPT. Kagi making critical business decisions (and in the process breaking a promise for early adopters) based on feedback from a gaming chat app is another reason to stop giving them money.

I don't get why you'd consider this a "bait and switch". It seems pretty unsurprising to me that a company testing out an uncommon, unproven business model would get the pricing wrong on the first attempt.

Regardless, it's not like they're the only game in town, or that you're locked in to some long-term contract with them. If you don't like the new pricing, cancel and go back to an ad-supported/data-mining-supported search engine.

From them last year:

... it's a bait and switch. How could you trust their promised privacy angle when they can't honor their own promises for pricing? All the privacy angle is is trust, I anticipate they'll abandon that too when it doesn't make economic sense.

This is a bit confusing, but the UX around is also not great.

Can't we have some basic place where we can see our alotted number of searches for one, especially as it's now set to change? On top of how there's not only new and changed tiers, but also separate legacy tiers. Going through a number of clicks in Billing just to see what our search frequency was the past months is kind of a pain.

Rather than having to stay up to day with news, a more intuitive interface for this would help a lot. Worst-case scenario is that loyal customers get a surprise bill next month.

I am a paid user of Kagi. I absolutely love the search. It is fantastic compared to Google which I have almost completely stopped using due to declining quality.

I think that while the pricing is probably quite reasonable when considering the costs involved in search, Kagi is up against a mentality that web search is free. Because that has been the way it has been for all people's memory. I know it has never really been "free" because our data has been exploited by Google, and the likes. However, most people don't think that far - as is evident by the fact that Google, et al grew to the behemoths that they have become.

I think they will probably need some way to ease people in to the idea of search being a paid service.

Now, I live in one of the richest countries in the world, and when I pitch Kagi Seach to my friends, family and co-workers, they balk at the idea of it being a paid service.

Some of these people are software engineers or IT professionals who rely heavily on search and who stands to benefit the most from the increased quality. And these are the same people who often complains about Google's declining search quality and SEO spam, etc. But still, Google is "Good Enough" and it is "free". So this is what Kagi is up against.

So I think they probably need some better free tier to get people to actually experience the difference in quality. I know that the free tier is likely a huge loss leader and there is some limit to how much Kagi can provide as free.

I have thought about this quite a lot since started using Kagi initially with a free tier account. My free tier account is limited to N searches per month. I run out of that number of searches in a typical workday. Problem is that I set my default search engine to Kagi on all my devices. This means that when I just type some single word just to get to a website, say, "reddit", "amazon", etc. That counts towards my limit. So that when I actually need a quality search result because I need to search for a solution to some rare error condition or similar, then I will have run out of free searches.

So one idea I have thought a bit about is: not all searches are equal. This goes both for the value of the search result for the user as well as the cost of executing the search query. Some common terms like one word queries such as "facebook", "amazon", "apple", etc. would likely be trivial to cache and thus not cost as complex queries that are also likely unique.

I think they should consider making non-unique, one word searches does not count towards the limit. And I would also strongly consider not having such queries require a login. The reason being that this would let many more people get started with Kagi.

And also, if I am to pay even a single cent for a search that is trivial, I would go out of my way to ensure that Kagi is not a default search engine on any devices and I would try my search on one of the other engines first. Even if the cost is trivial - but it is still there and it is something I am conscious about. And what is worse: I now have a variable cost I need to worry about...

Also, I think they really need to get companies on board for this. But most companies have very strict policies regarding recurring fees.

That is, until the mentality around search being free changes... And solving that will likely require investing a lot in giving free searches away. It's a marketing cost. And people really need to experience how the quality and experience of search can be better than Google. Because even though Google sucks most people have a hard time envisioning what an alternative would look like.

I have to admit, I'm a bit disappointed by the mostly negative responses here, I wouldn't have thought this would be received as badly as it apparently is, by this here crowd.

I haven't followed along that closely, but I dropped by their discord every once in a while, and from the discussions I saw I felt Kagi was as open as they could be, trying to communicate the upcoming change(s), why they are necessary, getting user input, changing their plans accordingly, etc.

So, maybe my expectations where already 'anchored', but I find those changes very reasonable, and only if you compare it with 'free' is it expensive. But as we all know, 'free' doesn't necessarily mean no money is involved, just who pays directly and who pays indirectly. I'd guess the 'actual' cost is close to the same in both cases, minus some scaling that Google can do and Kagi can't. I'm willing to pay for 'unscaled', personally.

I've been using Kagi for about a year now, averaging between 700 and 1200 searches per month, so none of the proposed plans would break the bank, compared to what I've been paying so far. Tempting to choose the legacy plan for a year, but I'll probably just go for the 'ultimate' one, the yearly plan, to support a service I really really don't want to go away.

During the time I've been using Kagi, I hardly noticed it. Which I think is brilliant. There was no annoyance, in probably 90% of my searches I don't even have to scroll and one of the first 5 results is what I'm looking for. No ads, at all. In my calculations, that are at least 700 interactions with software that are fast and to the point, with very little chance to annoy me, reliably, every month. And those interactions are very important for me to do my job. I value the time and piece of mind that are connected to those 700-1200 interactions.

So -- as a professional -- to me this is worth $25 a month, easily. I dislike subscriptions as much as the next person, but to me it seems obvious that the context matters here: if it's for a software, then I really want the option to pay for a permanent license, and I think it's fair to pay for (major) upgrades if I want them. Companies that lock you into their product and you can't use the data you created with it anymore -- unless you keep paying -- are acting morally reprehensible in my view.

But on the other hand, if the service that is provided has a considerable cost for every user-interaction, then, well, 'pay-per-view' is justified. If I use it more, then I have to pay more. I don't want companies to make a loss because I'm using their service, esp. if I like their service. And I even want them to make a healthy surplus. A business model where heavy users pay more and are not subsidized by low-volume users seems like a good thing to me.

If a search costs them, say, $0.02, then I'm happy to pay $0.04 for it, it is what it is. Of course I'd want them to be efficient, and save as much cost as one can reasonably expect (maybe some of my searches could be answered from my personal cache?), but from what I see, kagi hasn't been buying villas and yachts from my money so far, and I don't think they'll be able to in the near future with their new pricing structure.

What kagi was doing here ticks all of my boxes, I don't think they have been 'baiting & switching' me, and I trust their reasoning and calculations unless someone has good evidence that shows I shouldn't.

Chiming in to say I feel exactly this way too.

Me too. I think the cost/benefit calculus is pretty simple. The pricing is around 1.5 cents per search. Let's say someone does 600 searches, which is about what I do in a month, or around 20 per day. That costs around $10.

For someone with a net income of $20 per hour (a lot of people in the US), that's 30 minutes of time. Can Kagi save 30 minutes over 600 searches in a month, or 1 minute per day over 20 searches? I'm pretty sure it can easily, yes. The result quality for me is far better than DDG (which I'd realistically be using otherwise, for privacy reasons) or even Google.

Their costs have been soaring as they add more and more features which are literally meaningless to me.

I didn’t care about that, because they promised me my reasonable plan was grandfathered forever. That was a lie, so I canceled. Cause and effect. I don’t trust companies who lie to me.

I pay $20 for ChatGPT which is WAY more useful to me than Kagi. Hell, I pay half of that for Office subscription which I use even more. There is no way I can justify paying $25 for a search engine. And I am a professional too, just one who cares about money.

If you're a Kagi fan, the use of Discord by the search engine may seem impressive, but as a regular user looking for an affordable and trustworthy search engine, it's unlikely that you would spend your time engaging with the search engine's Discord community.

It's a common occurrence among startups to rely on Discord as a means to measure software usage, but in actuality, the platform mostly attracts highly engaged power users and a few followers who may not represent the average user. As a result, the company's perception of their software's typical user may be skewed.

I don't consider myself a kagi fan, nor do I think their use of discord is 'impressive'. That would be quite silly. So you are wrong if you assume that is where my positive judgement comes from. I just make different value judgements than you -- ones I feel align well with my own, personal priorities and specific context. That doesn't mean I don't care about money, I hope you can see and accept that.

I just stumbled upon their discussion about pricing, and found it interesting how such a problem could be approached, and seeing their point of view and reasonings, and pros and cons for several options, and how its a really difficult problem for a young company like them. Compared to that, the discussion here feels a bit one-dimensional and flat, tbh. Anyway, just wanted to give a different, bit more emphathetic perspective to most of the sentiments in the rest of the comments.

Basically, I can understand why they felt the need to make the decisions they made, but I acknowledge that I'm in the minority with this. Doesn't mean I don't think I'm right and you're all wrong :)

I'm happy to pay the money for search, but what's happening here seems to be Kagi jacking up the prices to pay for their other non-search stuff that I'm not interested in.

Sad to see this. I just cancelled my plan. To stay on an unlimited plan is over a 100% increase in price and that's just unacceptable to me.

The pricing at 10$ a month (paid as 120$ a month) was for me already too steep. But I could justify a subscription last june because of 3 reasons:

1. Philosophically: I want to pay for things I use 2. Quality: They do provide the best results 3. Experimentation: I want to try out new things

The new pricing scheme has forced me to abandon it. When my current subscription stops in june it is back to Google.

This actually could be a business model (in a very dirty way) for something that I prototyped years ago, that really didn't have a business model behind it.

My thought was to make a personal search engine. i.e. it wasn't about indexing the internet (though perhaps there was value to that in combination), but to index what you've seen / your social network shares with you (easier when the APIs to said social networks were actually usable, that's sort of gone the way of the dodo).

The problem is, while searching what you've seen / social network shares with you is "nice", how often are you actually going to use it? My thought was to make a browser extension that would make that passive, i.e. constantly show you what's related to the page you are looking at, from said index (using lucene's 'more like this' type search). My implementation was clean (not dirty like I said above), because it was all client side, nothing stored on any servers.

A dirty business model using a similar business model to this, would be to store everything online, and charge people to search their data, but they would be giving up all their privacy to this index then (hence the dirty part).

I also thought of targeted ads in the extension, but that would seemingly be a related privacy issue.

Yep, that's it for me. A loyal, paying customer all the way from beta days doesn't seem to matter much. I truly hoped they would have kept their word and grandfathered the old subscriptions.

Burning your money on the AI and browser nonesense is on you. Don't count me in.

Yeah, I will probably subscribe as they introduce the family mode.

Quality of the results is way better than Google and derivatives. I can once again find small blogs, various fora etc. with genuine people discussing their first-hand experience instead of generic ad farms.

let's mapreduce search

map search-term to several search engine (using curl, headless browser and whatnot)

then reduce / filter the results, removing ads etc, weighing duplicates more and punish irrelevants

the search-result is then piped to your favorite browser

That sounds like searx[0].

[0] https://docs.searxng.org/

That exists since 1996 :-)

https://en.wikipedia.org/wiki/MetaGer

One question I ask myself. Does the dependency to Google and Bing APIs been advertised before today ? Can't remember reading that and was genuinely thinking everything was baked in-house (yes I was naive.)

Yes, it is not something they hide. This has been discussed every time Kagi comes up, so I'd say it's fairly well known, at least in places where Kagi is known.

It is documented plainly in their help text and archive.org has indexed that page as far back as October.

https://web.archive.org/web/20221025065617/https://help.kagi...

Thank you for your documented answer !

I switched from Kagi back to Google because Kagi was just too slow for me. The search results on Google load much faster, while the response time on Kagi was at times over 500 miliseconds.

Why not SearX, You.com, Startpage, Neeva, etc?

Wondering what kind of legal exposure Kagi has here? In the United States, selling something under false pretenses (like the promise of grandfathered pricing) is fraud.

Maybe make the pricing not how many searches, but more about latency between searches for a session:

Sounds good, at my current kagi usage I barely topped 1k search in the highest month so far. Since I'll transfer to legacy professional I'll get 1k free so that's all good.

Tempting to get a 1 year sub but then the limiting of AI tools might be annoying. Hmm. Also not clear, if you hit AI tool limits on a legacy pro account can you pay per use?

Apparently they're struggling gathering money. It's not hard to imagine though.

>the $10 per month unlimited search plan was not financially sustainable for us

The correct response to realizing your business model is unsustainable is not to double down on it.

Beware the Ides of March.

I thought people hate subscription model, yet there are enough people willing to pay a monthly fee for search that is only marginally better than free product? I'm really confused. At least Adobe products etc. are actually miles ahead of alternatives.

Their target market is people who don't want ads and don't want their search behavior sold to third parties. Having better (or at least similar) search quality is certainly a requirement, but that's not really what people are paying for.

Search privacy may not be something you care about, and that's fine, but it seems like Kagi may have found a market that can sustain their model.

One of the big reasons I paid for Kagi was to support alternatives to Google.

Aside from that, it was also a good search engine worth paying for.

We are not a hivemind, I'll have you know.

And it is much better than Google Search. I don't get bombarded with ads and the results are actually relevant. Google is noticeably worse for me unless I'm searching info on local businesses.

I just use adblock.

That's not really a fair comparison, ad blockers don't help with rankings. You might not see literal ads, but Google will still serve you more SEO garbage than Kagi, which is IMO better out of the box and also allows you to uprank, downrank or block certain domains from results.

Even if it weren't marginally better, I'm paying to preserve my privacy and keep Google from monetizing my personal information.

You have a unique Kagi ID tied to your payment information. That’s not private.

It’s a lot more private than using Google, who are actively monetizing your information.

Never heard of this & I'm never going to pay for search for sure either

I am sorry, I said this when they first went pay. Vlad does not seem like a nice guy. My emails that I have exchanged with him have been very short and to the point of "he is better and knows better". I do not pay for their service due to this as well as I do not see the value. I didn't see the value with their old model, and see the value even less now. I give them another year or 2 and they will be a relic of the past. This price hike and the broken promises are a clear indication they are struggling. Welcome to the deep end of the pool, how long can you tread water?

>I didn't see the value with their old model, and see the value even less now.

I do see the value and would be happy to pay for the $25/month unlimited plan.

Search and AI are the largest boons to my productivity by a long shot. $25/month is nothing when the alternatives (Google, Bing, DuckDuckGo) all suck. If it was $25/day I would start to question the pricing.

While I value your thoughts, judging by the other comments on here, you are in the minority. I REALLY did/do want to like them and their product. Being on a Mac, I have tested both their standard and beta browser. It is decent. However, after seeing Kagi go from free to paid and now being even more, I see the same happening with their browser down the road. I just do not want to invest my time into an experiment only to be treated the way they have to their users. It is just shady.

The proper way to charge for search is free with ads with an optional premium model that promises not to data mine you or show ads. I would pay for Google search if they removed all the ads, and as a bonus aggressively de-ranked content that was primarily focused on ads rather than useful information.

There will be a company that dethrones Google in search, but it might take some time

Reply on news.ycombinator.com