Excited for the deepseek release this week (or at least they announced they'd release this week). Hopefully they also push even closer to SOTA.

▲

bayesianbot 5 hours ago | parent | next [-]

That is exciting!

I don't understand how DeepSeek can be so cheap with their cache pricing - ~0.003 usd / 1Mtok. 100x less than Kimi K3, or similar numbers against pretty much any other decently sized model to my knowledge. I've been using it whenever possible as even longer agent sessions cost few cents.

▲

sudosysgen 5 hours ago | parent | next [-]

If you read DeepSeek's papers, you'll find a litany of architectural features that allow for a greatly reduced cache hit price by shrinking the size of the KV-cache.

▲

yfontana 5 hours ago | parent [-]

How come no other big model seems to be able to deliver the same type of extremely low cache cost though, if their techniques are public?

▲

jboss10 4 hours ago | parent | next [-]

I think the "architectural features" are part of the model, not the kv cache. So implementing it would be difficult and expensive.

▲

petu 4 hours ago | parent | prev | next [-]

Deepseek V4 paper is just ~three months old

▲

sudosysgen 4 hours ago | parent | prev [-]

Many of these techniques haven't been published very long ago - it often takes a good 6-8 months for techniques to percolate. But also, they come at a complexity cost and, seemingly, also at a stability cost.

	▲	hnfong an hour ago \| parent [-]
		Also potentially a performance (in terms of output quality) cost. DeepSeek is cheap on a per token basis but lags behind in the benchmarks, perhaps it was a calculated tradeoff.

▲

hack1312 5 hours ago | parent | prev [-]

What provider are you using?

▲

bayesianbot 5 hours ago | parent [-]

DeepSeek's own API

▲

greyb 5 hours ago | parent [-]

Any way to avoid China sales tax or is that just the cost of doing business?

	▲	NortySpock 5 hours ago \| parent \| next [-]
		https://openrouter.ai/deepseek/deepseek-v4-pro#providers Look through the provider list for a company you are willing to do business with?
	▲	anigbrowl an hour ago \| parent \| prev \| next [-]
		Good grief, the sales tax is only 6% on a service that's already extremely affordable.
	▲	verdverm 4 hours ago \| parent \| prev [-]
		Fireworks.ai

▲

kamranjon 5 hours ago | parent | prev | next [-]

Where did you hear about the deepseek release? Would love to follow the same source.

	▲	benjiro29 3 hours ago \| parent \| next [-]
		> Where did you hear about the deepseek release? * Tons of gray testing going on for the last 2+ weeks (people at random getting the new v4 model for a while before its removed again). * It also DeepSeek their 3th birthday this Friday. * The its been almost 3 months from the v4 DeepSeek release, and the model everybody have been using, was not post-trained. That is what they have been doing during this time. People trying out the new DSv4 via the web chat with quick game creation tests. People pulling out stuff like Stellaris clones etc. https://cct124.github.io/HORIZON6_DEMO/ https://www.showyourcode.app/zh/share/pmpwkamrnai2ue The Battlefront like game is impressive. Sure, the soldiers are backwards and the graphics are still kind of basic. But the entire movement system (run/walk/crouch/jump), gun mechanics, grenades, capture points, AI fighting / capturing back, etc ... Ended up playing it way too darn long lol The text is in mandarin but its not too hard to figure out the menu. Sniper is OP ;) The Horizon 6 game has everywhere mesh colliders, shows when you off track dirt being kicked up, etc ... In general, both example are very well polished minus the reverse soldiers issue. And the price is supposed to stay the same (beyond the doubling during Chinese workhours), because everybody got that update.
	▲	blovescoffee 5 hours ago \| parent \| prev [-]
		They emailed current paying users of the api (or at least that’s how I got updated).

▲

surgical_fire 4 hours ago | parent | prev [-]

Ohh I didn't know about it. Finally something to be excited about.