Kimi K3-256k
www.kimi.com - 187 poäng - 43 kommentarer - 5533 sekunder sedan
Kommentarer (13)
- illithid0 - 3080 sekunder sedanThis was posted 38 minutes ago, and as of 20 minutes ago, several Anthropic services are now designated as having a "major outage".
Doubt these are related, but it made me laugh a little.
- wren6991 - 565 sekunder sedanThis seems functionally similar to OpenAI having a step in pricing once you exceed a certain context length (also at 272k aka 2^18 aka 256k).
Having a lot of active context increases the per-token cost (flops issued and bytes read per token out) so it makes sense to pass that cost on to users. I'm actually surprised it's implemented as a hard cutoff instead of a smooth gradient.
- madihaa - 4792 sekunder sedanThat's actually nice! I usually try to stay below 200k context anyway.
- hawtads - 4359 sekunder sedanThis is just an API level change right? The model itself should be the same I think.
- dgritsko - 3897 sekunder sedanThis isn't quantized, right? Just a smaller context?
- periodjet - 997 sekunder sedanWhy are Anthropic and OpenAI even allowing their coding harness apps to be plugged into different model providers…? I’m surprised they haven’t figured out a way to clamp down on that by now.
- wxw - 3922 sekunder sedan> k3-256k is now available. Within 256k context, it delivers the same results. k3 (1M) consumes about twice as much quota as k3-256k.
- lukan - 3101 sekunder sedanSince Claude is the first time for me really, really out (TIL against my wished about https://status.claude.com/), I am now interested enough to see what else works. But ... when I click pricing, I see "Join a waitlist". Wtf? Are they really that good, so were totally surprised and overwhelmed by the requests, is this a marketing stunt, or do they just don't have the hardware being in china?
- hendersoon - 1690 sekunder sedanWhat is the purpose of this? Just a hard cutoff below the actual context window? You could set that in your harness anyway.
- sergiotapia - 2264 sekunder sedanI can't seem to find pricing for this model. Since the context size is just a quarter of the full size K3, is the price also much cheaper?
I usually keep my context in chats below 256k anyways so this would be tremendous honestly.
- holoduke - 1339 sekunder sedanA bit of topic. But how likely is it that the US will restrict Chinese open weight models and also force Euro countries to do the same? I think it will be effective within 6 months. The US is having a hard time staying competitive.
- ibuildproducts - 3699 sekunder sedanomg! new model!!
- superloika - 4716 sekunder sedanThe bells tolled today, but nobody came to church.
Nördnytt! 🤓