Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Kimi K2.7-Code: open-source coding model with better token efficiency

huggingface.co

Post reply on HN
Print view View original

11–20 of 254 posts

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#11

Post by jackdoe »

I think there is some threshold after which "best" model doesn't matter, we are not that far from it. Fable now is really good, in a year or so, if Kimi catches up, even if Fable6 is much better, I think I will use kimi at 1/10th of the price.

I said that about opus 4.5 at the time, thinking "this is so good, in 6-12 months the Chinese models will be as good and cheap, I will use them", but I was wrong.. I pay premium for opus4.7/8 and Fable.

But at some point, it will just do the thing you want it to do, and then the race to the bottom will start.

Now that Chinese companies have access to some very good Fable tokens, I hope it speeds up the race.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#13

Post by ramon156 »

shreedx wrote: post #10

I would really love to know if anyone has any experience with something like opencode + Kimi K2.6/2.7 now compared to Claude Code. What is better, what is worse, what is the cost comparison. I am currently paying $100 for the 5x Max plan, but Fable is running through the usage limits quite drastically and I cannot really say it's night and day compared to Opus. Also, I use this mostly for my side projects, so the $10…

I can only talk about GLM 5.1 which is roughly at sonnet 4 levels imo.

It's good, does most tasks well that I throw at it, but will fail at anything congitive/complex. It gets stuck often. It costs ~6$ a month though

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#14

Post by re-thc »

shreedx wrote: post #10

I would really love to know if anyone has any experience with something like opencode + Kimi K2.6/2.7 now compared to Claude Code. What is better, what is worse, what is the cost comparison. I am currently paying $100 for the 5x Max plan, but Fable is running through the usage limits quite drastically and I cannot really say it's night and day compared to Opus. Also, I use this mostly for my side projects, so the $10…

The Kimi problem is it doesn’t follow instructions and goes off track often.

Other than that it’s pretty decent (for the price).

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#15

Post by re-thc »

yanis_t wrote: post #2

I was wondering how does Anthropic and likes keep competitive when Opus is ($5 / $25) 5x times more expensive compared to Kimi K2.6 ($0.7 / $3.4) or other Chinese models, while being only marginally better. My theory is that US enterprise just can't send data to Chinese and that's understandable, but is that "the moat"?

> My theory is that US enterprise just can't send data to Chinese

Lots of US providers are hosting these “open source” models so doubt that’s the problem.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#16

Post by Zoadian »

jackdoe wrote: post #11

I think there is some threshold after which "best" model doesn't matter, we are not that far from it. Fable now is really good, in a year or so, if Kimi catches up, even if Fable6 is much better, I think I will use kimi at 1/10th of the price. I said that about opus 4.5 at the time, thinking "this is so good, in 6-12 months the Chinese models will be as good and cheap, I will use them", but I was wrong.. I pay premiu…

price/token isnt the only thing relevant. if you have to ask the AI again, it'll cost you more than when it gets things right in the first place.

so better models may still be cheaper even if the price per token is higher.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#17

Post by DragonBooster »

bgins wrote: post #3

I am still very new to the open-weight/source models. If anyone is using them full-time, I’d really love to hear about the setup and how they perform, as I am considering moving my org off Anthropic products.

These models have open weights, but at the moment most flagship models are practically accessible only through third-party model providers. The main exception is models in the ~30B parameter range, which can still be run on consumer-grade GPUs. That said, even consumer GPUs have become increasingly expensive and difficult to justify in recent years.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#18

Post by reactordev »

re-thc wrote: post #14
shreedx wrote: post #10

I would really love to know if anyone has any experience with something like opencode + Kimi K2.6/2.7 now compared to Claude Code. What is better, what is worse, what is the cost comparison. I am currently paying $100 for the 5x Max plan, but Fable is running through the usage limits quite drastically and I cannot really say it's night and day compared to Opus. Also, I use this mostly for my side projects, so the $10…

The Kimi problem is it doesn’t follow instructions and goes off track often. Other than that it’s pretty decent (for the price).

This. It will try to fix and refactor things that don’t need fixing because it gets stuck trying to solve the problem at hand.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#19

Post by jackdoe »

Zoadian wrote: post #16
jackdoe wrote: post #11

I think there is some threshold after which "best" model doesn't matter, we are not that far from it. Fable now is really good, in a year or so, if Kimi catches up, even if Fable6 is much better, I think I will use kimi at 1/10th of the price. I said that about opus 4.5 at the time, thinking "this is so good, in 6-12 months the Chinese models will be as good and cheap, I will use them", but I was wrong.. I pay premiu…

price/token isnt the only thing relevant. if you have to ask the AI again, it'll cost you more than when it gets things right in the first place. so better models may still be cheaper even if the price per token is higher.

yes, that is my point, but at some point, better is unmeasurable, and both the better and the not-as-good produce similar result, and then you pick the one with 1/10th of the price
Post reply on HN