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

Claude Haiku 4.5

anthropic.com

Post reply on HN
Print view View original

61–70 of 292 posts

Re: Claude Haiku 4.5

#61

Post by ilaksh »

What LLM do you guys use for fast inference for voice/phone agents? I feel like to get really good latency I need to "cheat" with Cerebras, groq or SambaNova.

Haiku 4.5 is very good but still seems to be adding a second of latency.

Re: Claude Haiku 4.5

#62

Post by Brendinooo »

dheera wrote: post #52
steveklabnik wrote: post #14

I am really interested in the future of Opus; is it going to be an absolute monster, and continue to be wildly expensive? Or is the leap from 4 -> 4.5 for it going to be more modest.

I wonder what the next smaller model after Haiku will be called. "Claude Phrase"?

Claude Couplet

Re: Claude Haiku 4.5

#64

Post by btown »

simonw wrote: post #18

Pretty cute pelican on a slightly dodgy bicycle: https://tools.simonwillison.net/svg-render#%3Csvg%20viewBox%...

Context on this cutting-edge benchmark for those unaware:

https://simonwillison.net/2025/Jun/6/six-months-in-llms/

https://simonwillison.net/tags/pelican-riding-a-bicycle/

Full verbose documentation on the methodology: https://news.ycombinator.com/item?id=44217852

Re: Claude Haiku 4.5

#66

Post by rudedogg »

minimaxir wrote: post #2

$1/M input tokens and $5/M output tokens is good compared to Claude Sonnet 4.5 but nowadays thanks to the pace of the industry developing smaller/faster LLMs for agentic coding, you can get comparable models priced for much lower which matters at the scale needed for agentic coding. Given that Sonnet is still a popular model for coding despite the much higher cost, I expect Haiku will get traction if the quality is a…

This also means API usage through Claude Code got more expensive (but better if benchmarks are to be believed)

Re: Claude Haiku 4.5

#67

Post by u8080 »

dheera wrote: post #52
steveklabnik wrote: post #14

I am really interested in the future of Opus; is it going to be an absolute monster, and continue to be wildly expensive? Or is the leap from 4 -> 4.5 for it going to be more modest.

I wonder what the next smaller model after Haiku will be called. "Claude Phrase"?

Claude Banger

Re: Claude Haiku 4.5

#68

Post by criemen »

nthypes wrote: post #65
criemen wrote: post #43

Earlier quoted context omitted.

Fascinating, so I have to think more "pay for RAM/redis" than "pay for SSD"?

"pay for data on VRAM" RAM of GPU

But that doesn't make sense? Why would they keep the cache persistent in the VRAM of the GPU nodes, which are needed for model weights? Shouldn't they be able to swap in/out the kvcache of your prompt when you actually use it?

Re: Claude Haiku 4.5

#69

Post by minimaxir »

criemen wrote: post #68
nthypes wrote: post #65

Earlier quoted context omitted.

"pay for data on VRAM" RAM of GPU

But that doesn't make sense? Why would they keep the cache persistent in the VRAM of the GPU nodes, which are needed for model weights? Shouldn't they be able to swap in/out the kvcache of your prompt when you actually use it?

That is slow.

Re: Claude Haiku 4.5

#70

Post by justinbaker84 »

I am very excited about this. I am a freelance developer and getting responses 3x faster is totally worth the slightly reduced capability.

I expect I will be a lot more productive using this instead of claude 4.5 which has been my daily driver LLM since it came out.

Post reply on HN