> 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"?
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!
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 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 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.
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...
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.
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.
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.
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.
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.
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.
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.
> 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.
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.
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
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 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
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.
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?
> 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.
> 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.
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).
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?
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.
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.
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.
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.
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.
Also, they broke their promise from last year, saying that they'd grandfather-in all early adopters, as long as they don't cancel:
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.
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.
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.
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.
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.
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 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.
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. "
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.
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.
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.
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.
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.
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).
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.
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.
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.
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
> 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.
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.
233 comments
[ 3.0 ms ] story [ 237 ms ] threadI 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"?
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 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 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.
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.
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.
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.
I just updated my monthly subscription to annual for just that purpose.
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.
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.
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.
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.
Supposedly they are not doing it because of advantages of associating your payment method and searches.
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 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.
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.
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...
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.
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.
All this crap with AI and Kagi releasing a browser is a distraction from that.
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.
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 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.
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.
There will be a company that dethrones Google in search, but it might take some time
I have used Brave search that gives similar search results for way less money.
> Search limit reached.
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.
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
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.
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.
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).
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?
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.
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.
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.
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.
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.
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.
That’s odd. It seems like the most natural thing ever to me.
You get X free searches per month.
It doesn't seem dishonest or inaccurate to me at all.
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.
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
[0] https://docs.searxng.org/
https://en.wikipedia.org/wiki/MetaGer
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'.
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. "
Without even considering the early adopter benefit, this pricing update for me is a nothing-burger.
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 $9 more, slightly more than what you tipped them.
So what is wrong ?
And you are supporting their browser development. I mean I understand people want unlimited, but then you are already tipping them. So something must be missing here I am not getting it.
With the old pricing, it's unlimited searches for 10$ a month. With the new pricing, you're now limited to 1000 for this price.
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.
> 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.
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...
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 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
So it's optional, however they also say this: 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).
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.
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.
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.
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.
[1] http://teclis.com
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.
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
> 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"?
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.
Does anyone know of a workaround?
Firefox for Android
Settings > Accessibility > Zoom on all websites