DeepSeek V4 Flash 0731

This latest DeepSeek is almost at the "too cheap to meter" level. That's going to be a larger unlock than models like Fable/Mythos that are way too expensive to justify, IMO.

What secret sauce do they have?

How can OpenAI or Anthropic fight against these prices?! $0.14 input, $0.28 output. For 1M tokens...

One thing that popped into my head is that this shows how committed they are to building something that scales across the world

China has zero energy concerns in terms of energy production - not literally zero, but they’d be able to prioritize other dimensions and not necessarily worry about efficiency

Here they are though releasing models that sip resources

I love DeepSeek V4 Flash since the pre-0731, now even more. It is the first model that is truly too cheap to meter.

But I find it having a pretty significant problem with tool calling - no idea why, but tool calling with it is SLOW. As long as the model is reasoning, all good. But give it a bunch of tools and it becomes extremely slow.

Am I the only one experiencing this?

Finally something that is breaking away from the pack. Interesting that max costs less than high. I still think, currently, TPS is more important than near frontier intelligence. Likely for reasons that LeCun outlined, maybe out of a billion prompts you will get value from that intelligence. When we have very fast models abstraction will work as that filter.

It's serviceable but, like many Chinese models, it uses a lot of tokens to get work done.

so cool. does it mean it can understand the verificated code

The DeepSeek team is so strong, very impressive.

Imagine if they had GPU resources of western labs.

These prices are not real. They already said so.

[flagged]

[flagged]

Price is not a good meter. Active parameters per token are. Joule would be even better.

Price is confounded by VC subsidies, economies of scale, and inference optimizations. I think a more interesting chart would be ARC AGI vs forwards pass flops or ARC AGI vs training tokens. Of course we don't have those numbers for the closed source models or even some of the open weight ones.