391–400 of 423 posts
So, while the throughput was 400-500tps in beta its now ~150tps on OpenRouter. I was hoping for a bit more, but it's still 100% faster for a very good price, so I won't complain.
I'm using it right now and it's noticeably faster.
I'd also say, it seems smarter, but I think that's because of some harness updates I installed. (I haven't used pi for almost a month)
Earlier quoted context omitted.
If it's actually comparable in practice that would be very impressive. I am yet to try a DeepSeek model. From the pricing, it's 3x cheaper on cache, 1/3 more expensive on input, and equal on output compared to GPT 5.6 Luna. I would love to compare these two at work, where I pay API prices. At home I will stick to Astra and Fable.
Just out of curiosity, may I know why you pay API price at work versus using dozens of subscriptions that you APIfy?
Earlier quoted context omitted.
In this case "safety" means how to restrict access to good models for working class. You can be sure the rich have access to unrestricted and uncensored models.
I really don't think this is true at all. Do you have any evidence to suggest fully unrestricted frontier models are available for a price? Or...even exist?
[0] - https://learn.microsoft.com/en-us/azure/foundry/responsible-...
I'm a big fan of DeepSeek. Also, ask it what model it is :) In Pi (pi.dev), it tells me it's definitely Claude by Anthropic, via the API via curl it tells me it's "probably ChatGPT", its very funny.
I'm surprised more people aren't talking about the cache hit price: $0.003 per million tokens. I have a feeling that the price of 1 million tokens transmitted over the internet is more expensive than cache hit. Are we close to making the chat completion API obsolete because the cost of context transfer over network is going to dominate the task total cost? Here's the same token usage priced at different rates: a real…
Realistically, if you had it 5% utilized, those million tokens would cost you about $0.0000062, which is pretty insignificant compared to what they charge you. (Assuming one byte per token, ignoring compression)
I've run some evals on my puzzle game https://redactle.net/llm-leaderboard Deepseek v4.1 flash is able to solve it some of the time. I've found it burns through more reasoning tokens than any other model. Google models like Gemini 3.8 Flash are still dominating and is able to one-shot most evals while being the cheapest. I'm curious what other unique evals people are running.
Earlier quoted context omitted.
> welfare We should be paying attention to it just in case it ends up mattering enormously. It's cheap insurance. Aside from that, US labs' system cards have been pretty useless for a while—I think the last great one was the combined system card for Claude 4 Sonnet and Opus.
I always talk to models using grugspeak, like 'where getcontext used' I felt a bit bad about it, then I learned yday that model's internal thinking traces are also like this
https://github.com/JuliusBrussee/caveman/blob/main/skills/ca...