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

The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin

minimaxir.com

Post reply on HN
Print view View original

111–116 of 116 posts

Re: The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin

#111

Post by senordevnyc »

daveguy wrote: post #97
senordevnyc wrote: post #79

Earlier quoted context omitted.

Haha, I never tire of the AI haters downvoting stuff like this. Down with reality!!

Or, everyone finally realizes that token burn is not the same as productivity. Maybe they just down voted for the questionable spending brag.

We were talking about whether these metrics are meaningful. I was just pointing out that even a tiny one-person company can burn a lot of tokens.

As to whether the token spend is questionable, the number I quoted is for my production AI pipelines, not for coding. And my customers (and profit margin) seem to think the spending is valuable.

Re: The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin

#112

Post by minimaxir »

segmondy wrote: post #99
minimaxir wrote: post #94

Earlier quoted context omitted.

The post goes into that issue. Throughly. The numbers at the beginning of the post are weekly aggregate values well after the endpoint was paid-only.

The post is wrong, it's still free, see - https://openrouter.ai/tencent/hy3-preview:free it's free in kilo.ai https://kilo.ai/models/tencent-hy3-preview-free It's free in a lot of places.

The first endpoint was closed. If you actually try and call it from the API you get this response:

> Hy3 preview is no longer available as a free model. It has transitioned to a paid model. Continue using it here: https://openrouter.ai/tencent/hy3-preview

The Kilo Code may have free traffic but if you check the numbers is still inconsequential relative to the trillions of tokens through OpenRouter.

Re: The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin

#113

Post by alecco »

numlocked wrote: post #87
alecco wrote: post #32

PSA: Don't use OpenRouter for DeepSeek V4 as it messes up you caching. Use DeepSeek API directly and you'll get 2x to 3x more cached tokens.

Can you share more? I'm with OpenRouter and we would love to address this! We don't see this in our own testing, I don't believe -- but will share this feedback and dig in.

Just try. In a case last week it was ~3x and I tried multiple providers: deepseek, gmicloud/fp8, novita/fp8, and another one I can't remember. It was a large job where at least 2/3rds of the start of the prompts was exactly the same (literally a static string).

Then I read somewhere (I think X) that OpenRouter adds stuff and breaks caching (telemetry? headers? can't remember). So I stopped the job, switched to actual DeepSeek provider, and voilá, caching 3x more tokens per request (on average).

Re: The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin

#114

Post by phainopepla2 »

numlocked wrote: post #87
alecco wrote: post #32

PSA: Don't use OpenRouter for DeepSeek V4 as it messes up you caching. Use DeepSeek API directly and you'll get 2x to 3x more cached tokens.

Can you share more? I'm with OpenRouter and we would love to address this! We don't see this in our own testing, I don't believe -- but will share this feedback and dig in.

I am experiencing this using Opencode. Caching works fine via Deepseek API but not so good via Openrouter

Re: The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin

#115

Post by jaggs »

alecco wrote: post #32

PSA: Don't use OpenRouter for DeepSeek V4 as it messes up you caching. Use DeepSeek API directly and you'll get 2x to 3x more cached tokens.

Yes, I definitely noticed a problem with openrouter and deepseek v4 pro. It's much more expensive.

Re: The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin

#116

Post by alecco »

alecco wrote: post #113
numlocked wrote: post #87

Earlier quoted context omitted.

Can you share more? I'm with OpenRouter and we would love to address this! We don't see this in our own testing, I don't believe -- but will share this feedback and dig in.

Just try. In a case last week it was ~3x and I tried multiple providers: deepseek, gmicloud/fp8, novita/fp8, and another one I can't remember. It was a large job where at least 2/3rds of the start of the prompts was exactly the same (literally a static string). Then I read somewhere (I think X) that OpenRouter adds stuff and breaks caching (telemetry? headers? can't remember). So I stopped the job, switched to actual…

> switched to actual DeepSeek provider

I meant actual DeepSeek API.

Post reply on HN