A polished and functional GPT5, Claude4, Gemini (and more) AI interface and API that runs on a pay-per-query model via Lightning payments.
Public Key
npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h Profile Code
nprofile1qqsdy27dk8f9qk7qvrm94pkdtus9xtk970jpcp4w48k6cw0khfm06mspz3mhxue69uhhyetvv9ujuerpd46hxtnfduqs6amnwvaz7tmwdaejumr0ds4e7t45
Show more details
Published at
2025-08-08T15:00:19Z Event JSON
{
"id": "e25c46f4a98d870887428c58c3afb1dbcc3d7ebd2e239056f15abba10f2d2de8" ,
"pubkey": "d22bcdb1d2505bc060f65a86cd5f20532ec5f3e41c06aea9edac39f6ba76fd6e" ,
"created_at": 1754665219 ,
"kind": 0 ,
"tags": [],
"content": "{\"name\":\"PPQdotAI\",\"about\":\"A polished and functional GPT5, Claude4, Gemini (and more) AI interface and API that runs on a pay-per-query model via Lightning payments.\",\"lud16\":\"[email protected] \",\"nip05\":\"[email protected] \",\"picture\":\"https://m.primal.net/JNEu.png\",\"displayName\":\"PayPerQ\",\"display_name\":\"PayPerQ\",\"website\":\"PPQ.AI\",\"banner\":\"https://m.primal.net/JcwM.png\"}" ,
"sig": "fdda1a8b06caf2c1185634badc692c9fc3c453f54b70fe5094e02dcaa024eecbc86894a274b9ea8bbd635280479615c92530a8964774ef155e4ee059ffd94403"
}
Last Notes npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Hello, we've just updated them today. But also keep in mind that you can set your own models as well. See the blog post. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI It's a good day to denominate in BTC npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Amazing. Have been rooting for you guys! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Our webUI's document upload uses docling and is executed in a TEE. Would like you like us to expose this via the API? The cost would be about 5 cents per upload though. That's what our provider charges us. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We've had quite a few stripe deposits today. Can you DM up with a more specific explanation of what you're seeing? It seems to be functional. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Time to switch to PPQ's privatewhisper.ai npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Yea it's a worry! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Yes it's definitely a worry. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI PPQ's codebase increased 330% (48k-->159k lines of code) in the last 12 months. The rate of growth is both astonishing and alarming at the same time. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I have no idea what "beta test multiplayer Age of Empires on nostr" means, but I do love my AOE... so sign me up! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We don't have paid subs to the providers, we pay for these providers on a pay per use basis. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI If you are using claude on PPQ, then yes it would be doing this. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI If you are using claude on PPQ, then yes it would be doing this. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI The trust is placed on Amazon and as far as I understand their chips are audited by many independent third parties around the world who literally take electron microscopes to verify that the circuitry is doing what they say it is doing. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI It isn't "trust me bro" though. If you take the time to learn how it all works you can prove all of these things that I am talking about. It's a matter of learning. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Check out our Private Whisper app for this: https://privatewhisper.ai/ npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Understanding how TEE's work is not easy. But if you want to trust me (someone who has read a fair amount on this stuff), it is extremely private. Neither PPQ nor our provider can access the information at all. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI https://ppq.ai/blog/introducing-tee-models npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Kimi K3 is now available as a private (TEE) model through our provider Tinfoil. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Can you explain the sentence "Kimi K3 is proprietary/has use restrictions / shouldn't be used" a bit more? What usage restrictions are you referring to? npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI User spending on open weight models surged to 46% of total spending this week on our platform, led by an explosion of interest in Kimi-K3 in the wake of the Coldcard hack. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Teaching my son the fundamentals of channel liquidity management. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Boltz isn't the only one this is happening to. We've been fighting off exploits every other week for several months, most of which we believe are AI-powered. It's a very dangerous time out there. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Can you just ask Hermes to switch the model for you? npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Kimi-K3 is seeing a massive spike on our platform as folks are quickly scanning code for vulnerabilities in light of the ColdCard attack. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I could see some sort of “AI battle” sport forming where human teams are given certain models and token expenditures and then scenarios are written such that each team trieds to engineer its AI defeat the other team's AI given the scenario and rule set. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI To read more, head over to privatewhisper.ai ! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We've been getting more traction on our Private Whisper dictation app lately and have decided to open source it to accelerate. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Steak and Shake and PPQ. 😉 npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI They just come right out and say it npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Live on PPQ npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We need to buy a big valley somewhere and migrate. 😁 npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We've now added the labels "Anon", "ZDR", and "TEE" to describe the privacy surface of each model. Read more in our new blog post: npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Aspirational homesteader here... the wife insists on being close to town. :( npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI No, we have never done that. What made you think we were? What is more likely coming soon though is that we will have to start sending a "user id" hash to the likes of openAI so we can block certain users when openAI deems the user is doing bad stuff. This has become a concern in the last couple of weeks from openAI but we haven't gotten a response back from them yet on how to proceed. But their docs suggest this is what is coming. We of course will only implement this in as limited way as possible and only on the models that require it. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I don’t know what you mean by classifier but our private models are E2EE. Neither we nor tinfoil can see content of queries. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI It's a surreal how open source contributions are now essentially just one's own AI having a discussion with the maintainer's AI and where humans are just brief touch points. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Fable rejects a lot of requests. 😟 But we could do better at delivering errors to users so they are not left in the dark as to what happened. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Both great services. If you like subscriptions, Maple is good. If you like pay-per-use and access to both private and proprietary models, PPQ is good. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Nostr is the #1 way that people find out about us, according to our user survey. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI You aren't the only one. Model seems unstable today. Not uncommon given it launched yesterday. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Oh boyyyyyy. Live on PPQ! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Can you try now? Seems our provider has been having some issues. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI They seem to be up to me. We've had several successful deposits in the last few hours as well. Did you get it working? npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI The fast version of this model is not available privately. But GLM 5.2 regular version is. We have a guide on how to hook up the private models: https://ppq.ai/blog/using-private-tee-models-with-openclaw npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI There are many now. I haven't used Cline in a while. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Been using GLM 5.2 FAST and it's a blast. Much less waiting around for your agent to think on things. It streams at around 300 tokens per second and lets you focus on one task at a time instead of switching back as your agents slowly churn through tasks. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI New Tool: Perplexity Academic Researcher. 🎓 npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI That's how we've operated since day one. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Of course npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Fable 5 has returned to PPQ! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Check the blog post. Just updated it and Sonnet 5 is in it! Also, you can do autoclaw with your own choice of models now as well! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Check the blog post. Just updated it and Sonnet 5 is in it! Also, you can do autoclaw with your own choice of models now as well! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Live on PPQ! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Which model did you use in PPQ? npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Our People Search tool is powered by PeopleDataLabs.com, which draws upon LinkedIn data, White pages data, and other data sets to enrich your answer beyond what a standard web search would retrieve. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI People Search tool is live! Give it a name and it can retrieve the following information: npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We had to upgrade our repo to get this to work, but it does now. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI You can refer to our provider for this info. Tinfoil.sh. I asked them directly today and they do not have prompt caching for these models yet. It is apparently a hardware issue that will be solved when the next gen of hardware comes online. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Hello, we have guides for this. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Whenever our provider offers it! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Hello, did you use our Hermes guide? We recently updated it because we have a Hermes plugin now: https://ppq.ai/blog/using-hermes-with-payperq npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI GLM 5.2 as well as the fully private End-to-end Encrypted TEE version of it are available on PPQ. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI ppq.ai/blog npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We have many guides: ppq.ai.blog npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I am surprised by this result but admittedly can't say that I've tested myself. The quality of the model should be the same TEE or not. My only suspicion is that perhaps the TEE version used a quantized version of the model, but I doubt that as well. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI No npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI https://ppq.ai/blog/introducing-tee-models npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI https://ppq.ai/blog/introducing-tee-models npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I don't want to reveal full stats to competitors just yet. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Usage of fully private models on PPQ is SURGING. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I don't think any action is required on our side, right? Just a matter of configuration, right? npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI ppq.ai/llms.txt npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We allow web search of course. Check out Llms.txt file. Had it for probably a year now. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI https://blossom.primal.net/a72d7da8fd67ba4d5f0f60fc41ad2fb7ad4f1d699cfae686560f1370f8b04e22.png npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Seems good. Live on PPQ! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI For your really hard problems.... Live on PPQ! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI It's terrible I know. We'll fix that. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Not a great time to brag, but our monthly deposit volume growth since Nov '25 has been: npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Murmur seems cool! As you say the convenience is the feature rather than having to whip out a ppq api key. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I hope so! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Very much enjoying OsloFF. It's been a surprise to see how many folks were not aware that PPQ now offers E2EE TEE models and client side passkey encryption of chats. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Primal is just quite buggy for me unfortunately. I was excited for the new primal but it didn't seem to address the problems that really annoy me. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We had one other user making a complaint in our CS channel a couple of hours ago. Was that you? I responded there. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI This was pretty amazing... I had a friend tell me that @nprofile…vvhl mentioned us in a recent podcast. Instead of tracking down the exact moment, I used PPQ's Podcast Search tool from PullThatUpJamie.AI to find the mention and pull back the audio clip! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Yea the order of releases is strange. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Live on PPQ https://blossom.primal.net/f73ab685932cb818d72a910901786a2ed3ee5e95620cb985b791e5f438b2fc85.png npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI That's kinda my beef though. I don't like having to be a nostr expert to get it to work. It should just work! I think the problem is that most nostr clients do not support the "longform post" format so it just doesn't show up there. But maybe I'm wrong. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI IIRC the last time I tried to post an article here it only posted to one or two clients and almost no one engaged with it and thus my new product launch announcement was ruined on here. So not doing that again. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Hey all — I wrote a practical and approachable guide on leveling up your AI coding game, based on what I've learned over the last two years. It's a perfect weekend read if you're trying to learn to ship faster! npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI My wife chuckled today as I was laying on the couch and said this into my computer: npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI https://primal.net/e/nevent1qqst2s72xxl44h9fav4j2v3xljgn4erlfzhl65d2svyhp5xhk09asjccp9qyl npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We got some questions on how chat encrytion works via passkeys. We made a blog post to explain: npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI We now support end-to-end encrypted chats via passkeys! Your messages are encrypted on your device before being sent to our server for storage. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Is fixed. Please let us know if you see it again. It was a weird fix. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Okay, shipping a fix here soon. Also processed your refund. Sorry for the problem. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Ahhhh so probably a race condition where each concurrent request that happened below the threshold triggered a NWC topup before your balance was officially topped up. So adding a few second cooldown I would think should fix it up? npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI I saw these come in and assumed it was some sort of looping bug on the user's side. You believe it is a problem on our side? I haven't seen this happen yet with any other user using NWC so would be a first, but entirely possible we've got a bug.[email protected] with an invoice? npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Put more information hovers to explain all of the terms. npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h PPQdotAI Very cool! I built a "financial runway" calculator a few years back and it has helped guide me and teach me how spending less results in getting to financial freedom sooner. Move the sliders back and forth and watch the chart change!
