Right now in OpenRouter it's 3x/3.75x more expensive than V4 flash but the cache read is around 4x cheaper.

Why bother making a throwaway account only to post a comment that is obviously and blatantly wrong?

Read to learn but read to enjoy too. Sometimes you learn more not trying to learn.

Fair enough

There's no physical copy.

https://thinkinginpython.com/01_Introduction.html

Up to 4x but in 2 days.

I took this picture just after it when completely dark.

https://imgur.com/5kz8VyA

Right below the pricing it is stated that they plan to increase the prices in the near future.

"near future" is not "today"

It can be because the message has been there for some weeks now.

I've been using the last Deepseek Flash update for a week and I'm amazed. It was a capable model for easy tasks but now it looks like it can do some heavy development for peanuts.

I can't wait to try this new one.

IME I can't trust it to write it's own plans from a spec, but if I give it a detailed execution plan written by Opus, it's fast and cheap (if chatty) in executing it.

This is what I do, and it works fantastically well. Just make sure you have Opus/GPT review after.

Interesting. I use Flash for making the plans and GPT for execution.

flash for plans?! i don't understand why you wouldnt use something far stronger for the most load bearing point of the project

There aren’t many “far stronger” models than Flash 0731 now, it’s only beaten by Claude and OpenAI models at high/max effort, and everything that matches it costs 5x-10x more.

Price obviously

Depending on the language you're writing in and the problem domain, the smaller models can do dramatically better or worse.

I suspect in the future we'll see language-specific small models. "Coding" is still pretty broad as an activity. It'd be nice to be able to load up a model specific to, say, class-based Python and run it on-device.

Harmonic's Aristotle is a sort-of language specific model for Lean, if you want to see the future you described today.

You're doing it backwards.

I find DeepSeek flash incredible for the price and good in general if it has good plans. I will typically plan using Opus or GLM, then implement with DSF

I'm working on a browser IDLE game made with Go. I've never touched Go before. The game core it's 80% done and it was pretty easy to code but I have no idea what I'm doing in with the transport/http layer.

At this rate I'll have it finished by the end of the next decade.

I love idle games. What's it about?

It's a MMORPG. Combat, bosses, gathering and crafting professions, etc.

From the moment it launches, there should be enough content for around a year.

Dominus Automa is an idle mmorpg too - https://store.steampowered.com/app/3795810/Dominus_Automa/

Same style?

Not at all. It's a different concept.

More like https://store.steampowered.com/app/1267910/Melvor_Idle/

That's awesome! I 100%ed melvor idle and a bunch of the other big ones like antimatter dimensions, cookie clicker etc. Is there some way to get informed when you release it?

I thought no one here would be interested in it but I could post it to /show once it's ready.

I've been using DeepSeek Pro for a while and Flash only for certain dumb tasks where I only need the speed of a LLM and not big brains.

I find the newest OpenAI and Anthropic models to be way better for big tasks that require many decisions but I don't like that anyway because I lose track of what's being done.

Knowing what I want for every prompt makes DeepSeek Pro the best LLM for me. It allows me to work relatively fast at a very low price.