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

241–250 of 254 posts

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

#241

Post by port11 »

predkambrij wrote: post #161
kmike84 wrote: post #39

Earlier quoted context omitted.

I do have this experience. I've used Claude Code (with Opus mostly), and then switched to opencode (mostly with Kimi 2.6) for my personal projects; it's based on a couple months of use. Claude Code is better. But Opencode + kimi 2.6 is workable, which is big. For bare code writing, if you know what exactly you want, most popular models are fine (deepseek, kimi, etc), it feels more or less the same as anthropic models…

To my experience claude/codex $20 are even more subsidized, so running on sonnet or gpt5.4 again gives you more usage.

I wonder if they’re truly subsidised or if the API pricing is just massively inflated. Genuine doubt.

My CC stats show me using almost 300$ of Sonnet tokens on the 20$ plan. Is Anthropic willing to forgo 93% of the profit? A bit less than that but API is priced, say, 3x what it should be?

CC is great, but Sonnet (my main model) isn’t worth the API pricing. The cheap-but-good models arrive at similar results for much less (for context I’m using Aivo with CC).

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

#242

Post by port11 »

irthomasthomas wrote: post #181
kmike84 wrote: post #39

Earlier quoted context omitted.

I do have this experience. I've used Claude Code (with Opus mostly), and then switched to opencode (mostly with Kimi 2.6) for my personal projects; it's based on a couple months of use. Claude Code is better. But Opencode + kimi 2.6 is workable, which is big. For bare code writing, if you know what exactly you want, most popular models are fine (deepseek, kimi, etc), it feels more or less the same as anthropic models…

according to this opencode and cursor cli perform better than claude code: https://x.com/kunchenguid/status/2065345999682568593

The analysis at the bottom directly contradicts the statement.

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

#243

Post by danny_codes »

port11 wrote: post #241
predkambrij wrote: post #161

Earlier quoted context omitted.

To my experience claude/codex $20 are even more subsidized, so running on sonnet or gpt5.4 again gives you more usage.

I wonder if they’re truly subsidised or if the API pricing is just massively inflated. Genuine doubt. My CC stats show me using almost 300$ of Sonnet tokens on the 20$ plan. Is Anthropic willing to forgo 93% of the profit? A bit less than that but API is priced, say, 3x what it should be? CC is great, but Sonnet (my main model) isn’t worth the API pricing. The cheap-but-good models arrive at similar results for much…

Anthropic is making money from people who under-utilize their subscriptions, and presumably by sneaky throttling or not-sneaky throttling power users. Currently they are in an adoption race. Whether being first will actually let them "win" the market (and the market is a bit ill-defined) is unclear.

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

#244

Post by predkambrij »

port11 wrote: post #241
predkambrij wrote: post #161

Earlier quoted context omitted.

To my experience claude/codex $20 are even more subsidized, so running on sonnet or gpt5.4 again gives you more usage.

I wonder if they’re truly subsidised or if the API pricing is just massively inflated. Genuine doubt. My CC stats show me using almost 300$ of Sonnet tokens on the 20$ plan. Is Anthropic willing to forgo 93% of the profit? A bit less than that but API is priced, say, 3x what it should be? CC is great, but Sonnet (my main model) isn’t worth the API pricing. The cheap-but-good models arrive at similar results for much…

To my feeling, I'm getting usage of Opus (and Fable before the cut) that's greater than what I got from Sonnet last year. I reached $100 of usage when weekly was at 50%. This means, I could squeeze $800 worth of tokens for $20.

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

#245

Post by threethirtytwo »

SubiculumCode wrote: post #236
threethirtytwo wrote: post #223

Earlier quoted context omitted.

They are different and yet the same. The biggest difference is there’s generally more hatred for China because many us citizens are jealous. But corporate corruption is not that different in safety. Other than hatred the difference lies in incentives. Corporations want profit. China just wants to spy.

That is a.limitee understanding of China's ambitions here.

I’m Chinese bro. The American or international understanding of Chinese ambitions is a cartoon caricature of reality. You are ignorant.

In the context of LLMs spying is the biggest threat. The other biggest threat is information cover up. They don’t want the model to talk about embarrassing shit like tian men square.

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

#246

Post by arcanemachiner »

ignoramous wrote: post #218
arcanemachiner wrote: post #216

Earlier quoted context omitted.

The Go plan essentially gives you $50 of inference for $10 per month ($5 for the first month).

$60/mo currently: https://opencode.ai/docs/go/#usage-limits Their limits are staggered: 5h (max $12), weekly ($30), monthly ($60).

My mistake. You are correct.

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

#247

Post by AgentMasterRace »

varispeed wrote: post #68
schmorptron wrote: post #66

Earlier quoted context omitted.

Cursor's composer models are finetuned kimi

They are unusable (unless you want to deliberately destroy your codebase). So if Cursor's models are Kimi based, then well. I'll skip them altogether.

Composer is really good, but just like any Chinese model it needs a good plan. It's cheap and fast, in 1 month of pro I used the equivalent of 500$ in API credit for it.

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

#248

Post by cheema33 »

kennywinker wrote: post #91
esafak wrote: post #72

Earlier quoted context omitted.

I don't think "Chinese" is pejorative in this context any more than "American" is. They are one of the two ecosystems. What's wrong with saying "Japanese cars" today?

> What's wrong with saying "Japanese cars" today? Only that it’s a fairly meaningless grouping. When japan first entered the car market in north america there might have been some commonality, but now what characteristics do they share that some american cars don’t have? They’re not even imported a lot of the time. Given that, it does start to feel tinged with racism if someone insists on grouping things together tha…

> but now what characteristics do they share that some american cars don’t have?

The difference is quite big in my opinion. When given the option to pick a Japanese vs American vehicle for about the same price/features, most people will pick the Japanese vehicle. American vehicles have improved over the years, but quality and reliability are generally better for Japanese vehicles even today.

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

#249

Post by port11 »

predkambrij wrote: post #244
port11 wrote: post #241

Earlier quoted context omitted.

I wonder if they’re truly subsidised or if the API pricing is just massively inflated. Genuine doubt. My CC stats show me using almost 300$ of Sonnet tokens on the 20$ plan. Is Anthropic willing to forgo 93% of the profit? A bit less than that but API is priced, say, 3x what it should be? CC is great, but Sonnet (my main model) isn’t worth the API pricing. The cheap-but-good models arrive at similar results for much…

To my feeling, I'm getting usage of Opus (and Fable before the cut) that's greater than what I got from Sonnet last year. I reached $100 of usage when weekly was at 50%. This means, I could squeeze $800 worth of tokens for $20.

Anthropic has sent out a newsletter explaining they were more or less adding 50% (even 100%?) of quota to everyone, due to some great deal they made. That might be it. I do get lots more usage lately.

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

#250

Post by Implicated »

odiroot wrote: post #112
trollbridge wrote: post #32

Earlier quoted context omitted.

I am extremely happy with ohmypi, but you could use OpenCode or just keep using Claude Code! DeepSeek-V4-Pro is adequate plus use DS4-Flash for tasks or other small activity you’d use Haiku or Sonnet for. Go sign up with $10 prepaid. OpenCode Go - go sign up with $5 for a month and use Qwen-3.7-Max for design/plan/architecture or difficult troubleshooting. Feels closer to Opus 3.6 or 3.7 than DeepSeek, closest I’ve f…

> I am extremely happy with ohmypi, but you could use OpenCode or just keep using Claude Code! What's the benefit of using OMP over OpenCode? Just the sheer amount of options in OMP overwhelmed me. But I also use both via ACP in Zed so the CLI itself doesn't matter much.

I'm chime in here as another Pi user, starting with OMP and then just ditching it for vanilla Pi + MCP/LSP from OMP as well as pi-cursor-sdk to get access to Composer 2.5 through Pi. I use this as my 'fast' research & report (through my project/codebase) or boilerplate/tightly-specced implementation agent that's available to my planning/orchestrator (GPT 5.5 if complex backend work, Fable/Opus if wanting the extended context or view/design heavy work).

Pi has been great in this role, as well as occasional use not as a sub-agent but by my own human hands when I want to interact with the Composer 2.5 model directly... which I do much less these days as I just use Codex 5.5 /fast. Pi's great though.

Post reply on HN