OpenAI dropped the price of o3 by 80%

I actually contacted the California AG to get a refund from another AI company after they failed to refund me.

The AG office followed up and I got my refund. Worth my time to file because we should stop letting companies get away with this stuff where they show up with more requirements after paying.

Separately they also do not need my phone number after having my name, address and credit card.

Has anyone got info on why they are taking everyone’s phone number?

Doesn’t Sam Altman own a crypto currency company [1] that specifically collects biometric data to identify people?

Seems familiar…

[1] https://www.forbes.com/advisor/investing/cryptocurrency/what...

I also am using OpenRouter because OpenAI isn't a great fit for me. I also stopped using OpenAI because they expire your API credits even if you don't use them. Yeah, it's only $10, but I'm not spending another dime with them.

Interesting, it works for me through openrouter, without configured openai integration. Although, I have openai account and did verification with openai before. Conspiricy theory would say that they are exchanging PII so openrouter knows who am I :)

Welcome to tech dystopia.

Hello Human Resource, we have all your data, please upload your bio-metric identity, as well as your personal thoughts.

Building the next phase of a corporate totalitarian state, thank you for your cooperation.

Oh I also recently got locked out of my linkedin account until I supply data to Persona.

(So I’m remaining locked out of my linkedin account.)

Meanwhile the FSB and Mossad happily generate fake identities on demand.

I was excited about trying o3 for my apps but I'm not doing this validation.. thanks for the heads up.

I was more excited by the process, like, there exists a model out there so powerful it requires KYC

which, after using it, fair! It found a zero day

Thank you for reminding me why I’ll never touch these LLM services.

KYC requirement + OpenAI preserving all logs in the same week?

You are even luck to be able to verify. Mine give me an error about "Session expired" for months!! Support do not reply.

> How do I get my $20 back?

Contact support and ask for a refund. Then a charge back.

This feels eerily similar to a post I've read a within the last month. Either I'm having a deja vu, it's a coincidence that the same exact story is mentioned or theres something else going on

I suspect their data collection might not be legal in the EU.

https://withpersona.com/legal/privacy-policy

To me it looks like an extremely aggressive data pump.

As someone not in the US, I do a straight nope out whenever I see a Persona request. I advise everyone else to do the same. Afaik, it's used by LinkedIn and Doordash too.

this reminds me of how broadcom maintains the “free” tier of vmware.

With all this plus the saving of all chats they can't operate on the EU. But they do ....

I don't recall Persona being in the mix last year when I signed up. Interesting development.

>ID Check

Just send them a random passport photo from the Internet, what's the deal? Probably they are just vibe-verifying the photo with "Is it legit passport?" prompt anyways.

> OK, so now, we've gone from "I guess I'll give OpenAI a few bucks for API access" to "I need to verify my organization" to "There's no way in hell I'm agreeing to provide biometric data to a 3rd party I've never heard of that's a 'partner' of the largest AI company and Worldcoin founder. How do I get my $20 back?"

This should be illegal. How many are going to do the same as you, but then think that the effort/time/hassle they would waste to try to get their money back would not be worth it? At which point you've effectively donated money to a corp that implements anti-consumer anti-patterns.

Yeah, same. I am a paying API customer but I am not doing biometric KYC to talk to a bot.

This is in part "abuse prevention"[1] and in part marketing. Making customers feel like they're signing up to access state secrets makes the models seem more "special". Sama is well known to use these SV marketing tricks, like invite-only access, waiting lists, etc to psychologically manipulate users into thinking they're begging for entry to an exclusive club instead of just swiping a credit card to access an API.

Google tried this with Google Plus and Google Wave, failed spectacularly, and have ironically stopped with this idiotic "marketing by blocking potential users". I can access Gemini Pro 2.5 without providing a blood sample or signing parchment in triplicate.

[1] Not really though, because a significant percentage of OpenAI's revenue is from spammers and bulk-generation of SOE-optimised garbage. Those are valued customers!

Follow-up. I pasted the above into ChatGPT because I genuinely wanted to know how to get my 20 bucks back. That request is in and they say I'll get a response in 2-3 days. I then asked it "What are the potential risks of agreeing to their terms?" Here's the response:

Agreeing to Persona’s terms, especially for biometric identity verification, involves both privacy and long-term data security risks. Here’s a clear breakdown of the main risks you should be aware of: 1. Biometric Data Collection

Risk: Biometric identifiers (like facial recognition, voiceprints, etc.) are extremely sensitive and irreplaceable if compromised.

    What they collect: Persona may collect a selfie, video, and metadata, and extract biometric templates from those for facial comparison and liveness detection.

    If leaked or abused: Unlike passwords, you can't change your face. A future data breach or misuse could lead to permanent identity compromise.

 2. Data Storage & Retention

Risk: Persona says biometric data is kept for up to one year, but:

    You’re relying on their internal policies, not a legal guarantee.

    There’s no technical detail on how securely it’s stored or whether it’s encrypted at rest.

 Worst-case scenario: Poorly secured biometric templates could be stolen, reused, or matched against other data sets by bad actors or governments.
 3. Third-Party Sharing and Surveillance Risks

Risk: Your biometric and ID data may be shared with subprocessors (partners/vendors) that you haven’t explicitly vetted.

    Persona may transfer your data to cloud providers (like AWS, GCP), verification specialists, or fraud prevention services.

    Depending on jurisdiction, data could be subject to subpoenas, surveillance laws, or government backdoors (especially in the U.S.).

 4. Consent Ambiguity & Future Use

Risk: The fine print often includes vague consent for "quality assurance", "model improvement", or "fraud detection".

    This opens the door to retraining algorithms on your biometric data—even if anonymized, that's still a use of your body as data.

    Their privacy policy may evolve, and new uses of your data could be added later unless you opt out (which may not always be possible).

Should You Agree?

Only if:

    You absolutely need the service that requires this verification.

    You’re aware of the privacy tradeoff and are okay with it.

    You trust that Persona and its partners won’t misuse your biometric data—even a year down the line.

If you’re uneasy about this, you’re not alone. Many developers and privacy advocates refuse to verify with biometrics for non-critical services, and companies like OpenAI are increasingly facing criticism for requiring this.

Crazy, I already gave up registering for chatgpt because they asked for my phone number. I'm not giving that to any random startup.

Yeah, our models are sometimes too lazy. It’s not intentional, and future models will be less lazy.

When I worked at Netflix I sometimes heard the same speculation about intentionally bad recommendations, which people theorized would lower streaming and increase profit margins. It made even less sense there as streaming costs are usually less than a penny. In reality, it’s just hard to make perfect products!

(I work at OpenAI.)

Had a fun experience the other day asking "make a graph of [X] vs [Y]" (some chemistry calculations), and the response was blah blah blah explain explain "let me know if you want a graph of this!" Yeah ok thanks for offering.

I don't think that's laziness but maybe agent tuning.

It's just a highly unoptimized space. There is very little market consolidation at this point, everyone is trying things out that lead to wildly different outcomes and processes and costs, even though in the end it's always just a bunch of utf-8 characters. o3 was probably just super expensive to run, and now, apparently, it's not anymore and can beat sonnet/opus 4 on pricing. It's fairly wild.

This is almost certainly what they're doing and rebranding the original o3 model as "o3-pro"

I swear every time a new model is released it's great at first but then performance gets worse over time. I figured they were fine-tuning it to get rid of bad output which also nerfed the really good output. Now I'm wondering if they were quantizing it.

It's the same model, no quantization, no gimmicks.

In the API, we never make silent changes to models, as that would be super annoying to API developers [1]. In ChatGPT, it's a little less clear when we update models because we don't want to bombard regular users with version numbers in the UI, but it's still not totally silent/opaque - we document all model updates in the ChatGPT release notes [2].

[1] chatgpt-4o-latest is an exception; we explicitly update this model pointer without warning.

[2] ChatGPT Release Notes document our updates to gpt-4o and other models: https://help.openai.com/en/articles/6825453-chatgpt-release-...

(I work at OpenAI.)

From the announcement email:

> Today, we dropped the price of OpenAI o3 by 80%, bringing the cost down to $2 / 1M input tokens and $8 / 1M output tokens.

> We optimized our inference stack that serves o3—this is the same exact model, just cheaper.

I got 700+ tokens/sec on o3 after the announcement, I suspect it's very much a quantized version.

https://x.com/hyperknot/status/1932476190608036243

An OpenAI researcher claims it's the exact same model on X: https://x.com/aidan_mclau/status/1932507602216497608

Is this what happened to Gemini 2.5 Pro? It used to be very good, but it's started struggling on basic tasks.

The thing that gets me is it seems to be lying about fetching a web page. It will say things are there that were never on any version of the page and it sometimes takes multiple screenshots of the page to convince it that it's wrong.

I don't work for OAI so obviously I can't say for them. But we don't do this.

We don't make hobbyist mistakes of randomly YOLO trying various "quantization" methods that only happen after all training and claim it a day, at all. Quantization was done before it went live.

Are there any benchmarks that track historical performance?

> users found them more pleasing.

Some users. For me the drop was so huge it became almost unusable for the things I had used it for.

Quantization is a massive efficiency gain for near negligible drop in quality. If the tradeoff is quantization for an 80 percent price drop I would take that any day of the week.

Related, when o3 finally came out ARC-AGI updated their graph because it didn’t perform nearly as well as the version of o3 that “beat” the benchmark.

https://arcprize.org/blog/analyzing-o3-with-arc-agi

Even classic GPT-4 from March 2023 was quantized to 4.5 bits.

Hw about testing same input vs output with same seed on different dates. If its a different model it will return different output.

I think the API has some special IDs to check for reproducibility of the environment.

It's probably optimized in some way, but if the optimizations degrade performance, let's hope it is reflected in various benchmarks. One alternative hypothesis is that it's the same model, but in the early days they make it think "harder" and run a meta-process to collect training data for reinforcement learning for use on future models.

The API lists o3 and o3-2025-04-16 as the same thing with the same price. The date based models are set in stone.

You can just give it a go for very little money (in Windsurf it's 1x right now), and see what it does. There is no room for conspiracy here, because you can simple look at what it does. If you don't like it, so won't others, and then people will not use it. People are obviously very capable of (collectively) forming opinions on models, and then vote with their wallet.

you don't, so run your own model.

If the competition boils down to who has access to the largest amount of high quality data, it's hard to see how anyone but Google could win in the end: through Google Books they have scans of tens of millions of books, and published books are the highest quality texts there are.

Many would say Google's Gemini models are SOTA, although Claude seems to be doing well with coding tasks.

I have been using Google’s models the past couple months, and was surprised to see how sycophantic chatGPT is now. It’s not just at the start or end of responses, it’s interspaced within the markdown, with little substance. Asking it to change its style makes it overuse technical terms.

Deepseek was exciting because you could download their model. They are seemingly 3rd place and have been since Gemini 2.5.

Don't bother anyway. There are lots of cases of people trying and failing to go through the process, and there is no way to try a second time.

https://community.openai.com/t/session-expired-verify-organi...

https://community.openai.com/t/callback-from-persona-id-chec...

https://community.openai.com/t/verification-issue-on-second-...

https://community.openai.com/t/verification-not-working-and-...

https://community.openai.com/t/organization-verfication-fail...

https://community.openai.com/t/help-organization-could-not-b...

https://community.openai.com/t/to-verify-an-organization-acc...

Prevent Deepseek R2 being trained on it

200 per week now: https://x.com/kevinweil/status/1932565467736027597

My usage has also reflected the pretty heavy rate limits on o3. I find o4-mini-high to be quite good, but I agree that I would much rather use o3. Hoping this means an increase in the limits.

Before: 50 messages per week Now: 100 messages per week

"80% price drop" is just a title. The wall of criticism is for the fine-print.

The problem is your costs also scale with revenue. Ideally you want to have control costs as you scale (the first you build is expensive, but as you make more your costs come down).

For OpenAI, the more people use the product, the same you spend on compute unless they can supplement it with another ways of generating revenue.

I dont unfortunately think OpenAI will be able to hit sustained profitability (see Netflix for another example)

As an anecdote they have first mover advantage on me. I pay monthly but mostly because it’s good enough and I can’t be bothered to try a bunch out and switch. But if the dust settles and prices drop i would be motivated to switch. How much that matters maybe depends if their revenue comes from app users or API plans. And first mover only works once. Now they maybe coasting on name recognition, but otherwise new users maybe load balanced among all the options.

The moat is increasingly becoming having access to billions needed to finance the infrastructure needed to serve billions. That's why Google is still in the game. They have that and they are very good at massive scale and have some cost advantages there.

OpenAI is very good at this as well because of their brand name. For many people ChatGPT is all they know. That's the one that's in the news. That's the one everybody keeps talking about. They have many millions of paying users at this point.

This is a non trivial moat. If you can only be successful by not serving most of the market for cost reasons, then you can't be successful. It's how Google has been able to guard its search empire for a quarter century. It's easy to match what they do algorithmically. But then growing from a niche search engine that has maybe a few tens of thousands of users (e.g. Kagi) to Google scale serving essentially most of this planet (minus some fire walled countries like Russia and China), is a bit of a journey.

So Google rolling out search integration is a big deal. It means they are readying themselves for that scale and will have billions of users exposed to this soon.

> Their last funding round in March valued them at 300B. Despite losing 5B last year, they are growing really fast

Yes, they are valued based on world+dog needing agentic AIs and subscribing to the extent of tens or hundreds of dollars/month. It's going to outstrip revenue things like MS Office in its prime.

5B loss is peanuts compared to that. If they weren't burning that, their ambition level would be too low.

Uber now has a substantial portion of the month. They have about 3-4 billion revenue per month. A lot of cost obviously. But they managed 10B profit last year. And they are not done growing yet. They were overvalued at some point and then they crashed, but they are still there and it's a pretty healthy business at this point and that reflects in their stock price. It's basically valued higher now than at the time of the Softbank investment pre-IPO. Of course a lot of stuff needed to be sorted out for that to happen.

their moat is leaky because llm prices will be dropping forever and the only viable model will be a free model. Eventually everyone will catch up.

Plus there is the thing that "thinking models" can't really solve complex tasks / aren't really as good as they are believed to be .

I don't think the no moat approach makes sense. In a world where more an more content and interaction is done with and via LLMs, the data of your users chatting with your LLM is a super valuable dataset.

I mean sure, it's very promising if OpenAI's future is your only metric. It gets notably darker if you look at the broader picture of ChatGPT (and company)'s impact on our society.

* We have people uploading tons of zero-effort slop pieces to all manner of online storefronts, and making people less likely to buy overall because they assume everything is AI now

* We have an uncomfortable community of, to be blunt, actual cultists emerging around ChatGPT, doing all kinds of shit from annoying their friends and family all the way up to divorcing their spouses

* Education is struggling in all kinds of ways due to students using (and abusing) the tech, with already strained administrations struggling to figure out how to navigate it

Like yeah if your only metric is OpenAI's particular line going up, it's looking alright. And much like Uber, it's success seems to be corrosive to the society in which it operates. Is this supposed to be good news?

Gemini is close (if not better) so it just makes sense no? o3-pro might be ahead of pack tho

It'll be the opposite. Large tech companies are already running their own power plants.

It's one of the most unfortunate naming conventions

How are LLMs cached? Every prompt would be different so it's not clear how that would work. Unless you're talking about caching the model weights...

Have they ever decreased the price in the past? I don’t remember.

Presumably because the price was about 5x higher to begin with than any the competitors at the same tier of performance? Perhaps it's better to get paid anything at all than to just lose 100% of the customers.

Deepseek made a few major innovations allowing them to achieve major compute efficiency and then published them. My guess is that OpenAI just implemented these themselves.

Sure is - and o3 is missing from the OpenAI models that Azure is serving, which I suspect isn’t a coincidence - if OpenAI has some secret sauce that lets them undercut resellers this might shake up agreements for a bit.

Especially now that they are second in the race (behind Anthropic) and lot of free-to-download and free-to-use models are now starting to be viable competitors.

Once new MacBooks and iPhones have enough memory onboard this is going to be a disaster for OpenAI and other providers.

My understanding was that OpenAI couldn't make money at their previous price point, and I don't think operation and training cost have gone down sufficiently to make up for those short comings. So how are they going to make money by lowering the price by 80%?

I get the point is to be the last man standing, and poaching customers by lowering the price, and perhaps attract a few people who wouldn't have bought a subscription at the higher price. I just question how long investors can justify pouring money into OpenAI. OpenAI is also the poster child for modern AI, so if they fail the market will react badly.

Mostly I don't understand Silicon Valley venture capital, but dumping price, making wild purchases for investor money and mostly only leading on branding, why isn't this a sign that OpenAI is failing?

There was an article on here a week or two ago on batch inference.

Do you not think that batch inference gives at least a bit of a moat whereby unit costs fall with more prompts per unit of time, especially if models get more complicated and larger in the future?

for sure they are no longer clear winners, but they try to be just barely on top of others.

right now new Gemini surpassed their o3 (barely) in benchmarks for significantly less money so they cut pricing to be still competitive.

I bet they didn't released o4 not because it's not competitive, but because they are doing Nvidia game: release new product that is just enough better to convince people to buy it. so IMO they are holding full o4 model to have something to release after competition release something better that their top horse

LLM inferencing is race to the bottom but the service layers on top isn’t. People always pay much more for convenience, those are the thing OpenAI focuses on and is harder to replicate

Easy doesn’t mean cheap.

They need lots of energy and customers don’t pay much, if they pay at all

And then they all go out of business, since models cost a fortune to build, and their fan club is left staring at their computers trying to remember how to do anything without getting it served on a silver plate.

> "you've reached your usage limit!"

Just switch to a competitors free offering. There are enough to cycle through not to be hindered by limits. I wonder how much money I have cost those companies by now?

How anyone believes there is any moat for anyone here is beyond me.

o3 is so good it's worth paying for a minute (just for plus) just to see what it's like

I've never used anything like it. I think new Claude is similarly capable

Opus is really great but through Claude Code. If you used Cursor or RooCode it could be normal that you get disappointed

i found them all disappointing in their own ways. Atleast deepseek models actually listen to what i say instead of ignoring me doing their own thing like a toddler.

I think that was a joke. New pricing is already in place:

Input: $2.00 / 1M tokens

Cached input: $0.50 / 1M tokens

Output: $8.00 / 1M tokens

https://openai.com/api/pricing/

Now cheaper than gpt-4o and same price as gpt-4.1 (!).

Is the price drop really the reason for their recent outage?

Or is the price drop an attempt to cover up bad news about the outage with news about the price drop?

Why would that be?

Sounds like you want their Zero Data Retention plan: https://platform.openai.com/docs/guides/your-data#zero-data-...

(It's "contact us" pricing, so I have no idea how much that would set you back. I'm guessing it's not cheap.)