Update to Kagi Search Pricing(blog.kagi.com) |
Update to Kagi Search Pricing(blog.kagi.com) |
(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.
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.
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).
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!
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 :)
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.
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...
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.
You don't believe that Google is spending at least $44 million a day on providing search?
Most of their searches are combining data from Bing, Google and other sources.
They never stated that this cost is their infrastructure cost.
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.
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!
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.
The lenses are still garbage too, where "wiki.*" doesn't match "wiki.domain.tld".
Does anyone know of a workaround?
Firefox for Android
Settings > Accessibility > Zoom on all websites
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.
If I hadn't found this HN post, I wouldn't have been informed about any changes.
I've cross checked results when I got stuff I wasn't really expecting and it was nearly the same as google anyway.
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...
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.
> 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.
... 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.
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.
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 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 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.
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.
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.
Burning your money on the AI and browser nonesense is on you. Don't count me in.
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.
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
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...
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?
The correct response to realizing your business model is unsustainable is not to double down on it.
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.
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.
Aside from that, it was also a good search engine worth paying for.
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.
There will be a company that dethrones Google in search, but it might take some time
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 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 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.
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.
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 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'.
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.
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)
However, incorporating generative AI into search can be expensive, so we had to consider this in our pricing model.
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).
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.
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 using Kagi since they were in beta, but as soon as my subscription expires, I'm done...
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.
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.
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 :/
Without any proof there could be only trust.
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.
> 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 $20/mo (or whatever it ends up being) for search.
> And you are supporting their browser development.
I tried their browser. I didn't like it.
With the old pricing, it's unlimited searches for 10$ a month. With the new pricing, you're now limited to 1000 for this price.
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!
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:
> 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.
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.
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.
> 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.
- 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.
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.
They’re adding AI, where the human biases come baked in, and charging us extra for the insult.
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.
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.
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"?
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.
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.
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.
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.
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.
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.
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.
You get X free searches per month.
It doesn't seem dishonest or inaccurate to me at all.
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.
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 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.
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.
Looks like pay per view has finally come to web searches as well.
> Search limit reached.
Presumably though, they don't see this as sustainable. I wonder why? What kind of margin are they looking for here?
Moreover Bing increases pricing in May for their API and I guess they are trying to factor that in as well
I have used Brave search that gives similar search results for way less money.
I will probably move back to Brave Search.
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.
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.
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.
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.
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.
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.
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.
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.
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 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.
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.
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...
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.
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.
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.
All this crap with AI and Kagi releasing a browser is a distraction from that.
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
> 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.
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.
1: https://media.discordapp.net/attachments/925992877602000967/... (Backup: https://imgur.com/McoRELC )
> 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.
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.
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...
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...
Now they changed it to only the current billing period.
> 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.
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.
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.
That’s odd. It seems like the most natural thing ever to me.
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.
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
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.
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.
Google, the owner of the largest ad network in the world, does not make money from your searches? Are you trolling or completely misinformed?
IMO it's a moot point.
I just updated my monthly subscription to annual for just that purpose.
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.
> 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...
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"?
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.
So you changed the results, and now you are complaining because the results are changed? I don't get it.
Basically they are wishing the boost feature had room for more nuance.
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
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.
Without even considering the early adopter benefit, this pricing update for me is a nothing-burger.
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. "
Supposedly they are not doing it because of advantages of associating your payment method and searches.
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.
