THe more I think about this it should not be every month (this means the API is useful and the user should really pay for it - otherwise someone else has to pay for this cost). So perhaps a one time allotment like $2-$3 in API credits to test everything as you create a Kagi acount (and become a paid member) makes more sense?
But the whole point of this was to allow somewhat free access to tools like the Raycast extension for the average user.
Vlad FastGPT and other AI features are already unlimited for paying users, so if you set a cap on API requests monthly, it doesn’t seem much different. APIs are easier to automate and abuse, but a small monthly cap would pretty much stop it immediately. Even if it’s not super generous, it may attract more API users by letting them dip their toes in the water. For existing API users, it will offset their costs marginally.
FastGPT and other AI features are already unlimited for paying users
FastGPT is an experiment and at some time will be deprecated (the API will remain). Also if it became very popular we would need to lock it down as again someone has to pay for it and we are not in the business of providing free search.
AI features in Kagi are unlimited but in order to use "quick answers" you first need to perform a (paid) search. So the user is paying for the underlying search. And the main driver of cost we are talking about is not AI but underlying search.
Adding just a $1/mo free API allotment, automatically adds 20% cost for $5/mo plans and 10% for $10/mo plans to our cost base, and we do not have such margin to absorb. So the safe thing to do would be to offer a trial of the API and if it is worth paying for, users will, if it is not, then we should probably work on improving it.
This concept came up for me recently when thinking about how I could more effectively integrate Kagi into my phone usage. I think there are at least two reasons for wanting to use the API in general:
I am only focusing on the personal usage perspective. As a user, I want to be able to use Kagi in the most effective manner possible and retrieve information in a fashion that suits me personally in the context I am in at the time.
This concept exists in another form today -- Custom CSS. Kagi cannot please everyone with the default web interface, so Custom CSS offloads this responsibility to the user.
The API is another form of this. It would be great if Kagi provided an Android app or other phone interface so I could use it much like Google Assistant. However, Kagi resources are scarce. This work could be offloaded to Kagi users if API usage were available for personal use, and someone could build a Tasker integration or other phone interface and make it available. This makes Kagi more valuable without having Kagi do the work.
It's another level above Custom CSS -- Custom Interface.
As for cost: my argument is that I am going to perform the search, or use Universal Summarizer, regardless of whether I use the API or not. I may not be as pleased with the user experience, but I do want the information.
The benefit of having the API available for subscribers is that Kagi may get more subscribers if they know they can use alternative interfaces to Kagi. People may not want to even try Kagi if they can't get the same kind of Android or Raycast or Alfred integration they get with Google today. An API with personal use limits (which are the same limits, if they exist, as for the web interface) would allow this to happen.
I think a MVP version of this would be to provide a $2 floor of API credits each month to Ultimate users. If credits are >=$2, nothing is added, if <=$2, set it to $2. This adds incentive to subscribe to Ultimate, which has few benefits at the moment, and allows users to experiment with the API and build interfaces that may draw in more users in the future. (As before, I think "personal usage of API" should just be included, but implementing that is more work than adding a relatively safe amount of credits to Ultimate users.)
I bought the Professional Plan because I liked the sound of unlimited questions I could post to the FastGPT assistant. I tried it out on the website, and I found the results were good. Better than my experience on the common search engines—also, I was excited about all the integrations with my code editor of choice. Why leave my editor if I could get all my questions answered in right in my editor?
But I hadn't noticed that the unlimited questions only applies to the "web experience."—I had a chat with support where I was informed that the API require me to pay on top of the ~$100 I already payed.
So, I suggest the following—and I know I am no businessman, but hear me out: How about allowing "unlimted" questions via the API but with throttling. Say, a couple of questions per minute; and perhaps a dosen request pr hour. That way the "unlimited" API could be exposed but not abused.
Currently, I could automate a browser, and post from my editor via it and get answers to my questions, but that is just silly.
Just like any other API request, but limited to a handful of requests per minute, and a reasonable amount of requests pr hour.
This seems potentially related to this post: https://kagifeedback.org/d/1624-free-api-allotment-for-subscribers
Hi! I am an Ultimate Subscriber, and was surprised that I needed to pay additional for calls made to the !code bang outside the Orion Browser, for example, in Emacs, with FLOSS gptel (https://github.com/karthink/gptel)
It certainly makes more costly to use the AI for coding in the Code Editor of choice (pressumably, that's actually what most of us coders would want to do with AI for coding assistance!).
Why is it "free" to use it from the browser (Orion, for example), but it's required for more payments for code assistance?
If a user is already paying for !code assistance, it would be fantastic to get the same help in the code editor of choice!
It would be really nice to have a free allowance of 2-5$ in credits as ultimate user to power some smaller private projects and perform some tests.
Some sort of API access should be included with Professional and Ultimate. I think the Perplexity people do this the right way: Professional subscribers get a monthly $5 credit for API access. Need more? Buy more.
In Kagi's case, limiting this basic API access to Search will be appealing enough for most users.
Seconded - I'd hope to get at least some credits at the professional tier. I've been working on a Raycast extension (https://www.raycast.com/fearoffish/kagi-search) and I'd really like to use it more, but paying per search over my "unlimited search" plan is a real disincentive. I understand the fear of abuse, but a quota and a rate limit should do just that.
I really support the idea of adding monthly API credits for paid users. These days, not everyone is searching through a browser all the time. Many of us use different AI assistants or set up automated workflows, and being able to integrate Kagi into those tools would make the service even more valuable.
A fair use approach seems like the perfect solution. It allows users to get more out of their subscription in various ways while still keeping things sustainable and preventing abuse through reasonable limits.
Hope this can be rolled out soon!
