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

OpenRouter raises $113M Series B

openrouter.ai

Post reply on HN
Print view View original

101–110 of 279 posts

Re: OpenRouter raises $113M Series B

#101

Post by rkagerer »

GodelNumbering wrote: post #39
simonw wrote: post #6

It took me quite a while to come round to OpenRouter. Originally I didn't understand why anyone would put a proxy between them and an LLM, but it actually adds some quite significant value: 1. By far the lowest friction way to support and try out all the models. 2. They offer billing caps! Most model providers still don't do this [EDIT: maybe they do, see reply comment], but if you're going to run anything in public…

Another neat thing is, they publish hourly caching states for ALL model/provider combinations. I did some research on it to come up with a provider tiers list and found a bunch of open-source 3rd party hosts are simply trash tier https://dirac.run/posts/cache-hit-rates-agents

Agents push the full conversation history into context every turn

Why?

Maybe this is a dumb question, but why wouldn't an agent "keep the conversation going", like I do when interacting with an LLM through a web page? (I understand how it's impractical for long-running tasks where the agent has to wait days for the next input, but assume that's not the majority of use cases)

Re: OpenRouter raises $113M Series B

#102

Post by nickrj »

minimaxir wrote: post #2

As someone who uses OpenRouter extensively (and wrote an unintentional adjacent PR piece a few days ago: https://news.ycombinator.com/item?id=48317294 ), it's definitely the best way to try out new models without fiddling with each providers distinct APIs which is becoming a recurring concern as of late. That said, I don't understand the people who use something a full agentic backbone with expensive models like Clau…

[dead]

Re: OpenRouter raises $113M Series B

#104

Post by BoredPositron »

rkagerer wrote: post #101
GodelNumbering wrote: post #39

Earlier quoted context omitted.

Another neat thing is, they publish hourly caching states for ALL model/provider combinations. I did some research on it to come up with a provider tiers list and found a bunch of open-source 3rd party hosts are simply trash tier https://dirac.run/posts/cache-hit-rates-agents

Agents push the full conversation history into context every turn Why? Maybe this is a dumb question, but why wouldn't an agent "keep the conversation going", like I do when interacting with an LLM through a web page? (I understand how it's impractical for long-running tasks where the agent has to wait days for the next input, but assume that's not the majority of use cases)

The "web page" does the same you just don't see it.

Re: OpenRouter raises $113M Series B

#105

Post by BoredPositron »

brianwawok wrote: post #84
simonw wrote: post #6

It took me quite a while to come round to OpenRouter. Originally I didn't understand why anyone would put a proxy between them and an LLM, but it actually adds some quite significant value: 1. By far the lowest friction way to support and try out all the models. 2. They offer billing caps! Most model providers still don't do this [EDIT: maybe they do, see reply comment], but if you're going to run anything in public…

I’m just not sure they have a moat or a long term play? I put $20 in and tried a few models. Then I went right to the model provider to put in $1000 and avoid the middleman tax. Now imagine a big corp spending millions on AI. That’s a lot of middleman tax.

There are enough services that don't want the model provider to know who they are.

Re: OpenRouter raises $113M Series B

#107

Post by sosodev »

rkagerer wrote: post #101
GodelNumbering wrote: post #39

Earlier quoted context omitted.

Another neat thing is, they publish hourly caching states for ALL model/provider combinations. I did some research on it to come up with a provider tiers list and found a bunch of open-source 3rd party hosts are simply trash tier https://dirac.run/posts/cache-hit-rates-agents

Agents push the full conversation history into context every turn Why? Maybe this is a dumb question, but why wouldn't an agent "keep the conversation going", like I do when interacting with an LLM through a web page? (I understand how it's impractical for long-running tasks where the agent has to wait days for the next input, but assume that's not the majority of use cases)

I’m not sure I understand your question. Every interaction you have with a model in a web page does the same thing in the backend. It feeds the whole conversation history, perhaps with a bit of processing, into the model so it can process the next generation. Filling the context window is how these models retain coherence.

Re: OpenRouter raises $113M Series B

#108

Post by BoredPositron »

a13n wrote: post #17
simonw wrote: post #6

It took me quite a while to come round to OpenRouter. Originally I didn't understand why anyone would put a proxy between them and an LLM, but it actually adds some quite significant value: 1. By far the lowest friction way to support and try out all the models. 2. They offer billing caps! Most model providers still don't do this [EDIT: maybe they do, see reply comment], but if you're going to run anything in public…

Both OpenAI and Anthropic have billing caps… who doesn’t?

There is a scheme to send gifts with a compromised anthropic key even if the limit is reached.

Re: OpenRouter raises $113M Series B

#110

Post by antonkochubey »

zero-dark wrote: post #54

Congrats to the OpenRouter team for securing this round of funding. The 5% surcharge for their pricing model may not be palatable to enterprises. In fact, the OpenRouter team could be a pivotal part of the enterprise GenAI stack if they can allow configurable, pluggable endpoints for routing directly to enterprise vetted endpoints to 1P/3P LLM APIs. A couple of large companies I’ve worked so far kinda have this syste…

Enterprises are paying 500% - 20000% markup for AWS services so why do you think 5% will be a problem?
Post reply on HN