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

21–30 of 279 posts

Re: OpenRouter raises $113M Series B

#21

Post by simonw »

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?

Huh, so they do.

Anthropic: https://support.claude.com/en/articles/8977456-how-do-i-pay-... - you can pre-pay and get a hard cutoff.

OpenAI: https://community.openai.com/t/how-to-set-billing-limits-and... - last time I looked OpenAI had a soft but not hard limit, I guess they fixed that last year.

I remember bugging them both about this last year, I need to update my mental model!

Re: OpenRouter raises $113M Series B

#23

Post by vasco »

> ... with participation from NVentures (NVIDIA's venture capital arm), ServiceNow Ventures, MongoDB Ventures, Snowflake Ventures, Databricks Ventures ...

Are tech companies FOMOing so hard that they're now all running AI venture arms themselves instead of you know, developing their own products? Except for NVIDIA who needs to keep pumping the bubble I didn't expect the others.

Re: OpenRouter raises $113M Series B

#24

Post by alecco »

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…

At the moment for DeepSeek V4 it messes up caching and that's a key pricing feature for V4.

https://news.ycombinator.com/item?id=48319827

Re: OpenRouter raises $113M Series B

#25

Post by simonw »

maxloh wrote: post #18
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…

OpenRouter is merely only a proxy. They also host some open-weight models

I don't think they do. They proxy to a bunch of open-weight model hosts, but I've not seen that they host them themselves.

They don't list themselves on https://openrouter.ai/providers

Re: OpenRouter raises $113M Series B

#26

Post by tadfisher »

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?

Based on experience, Google Cloud. No idea if that translates to Gemini usage billing.

Re: OpenRouter raises $113M Series B

#27

Post by throw10920 »

I think that OpenRouter will continue to be very popular while there lots of experimentation in the LLM space, and while the "current favorite" model continues to change between various frontier labs.

After things begin to settle down, we'll probably see a consolidation of both frontier and open-source models - and then OpenRouter will become less useful, because that 5% overhead is well worth it when you want to try 20 models from 10 labs, but harder to stomach when you only need 5 models from 2 providers, and each of those providers has its own API knobs that you can tune to make things even cheaper.

Re: OpenRouter raises $113M Series B

#28

Post by alecco »

tom1337 wrote: post #9

Is the Open in OpenRouter the same as in Open AI? I couldn’t find any repository or hosted code. Thought it'd be a open source, self hostable tool with a cloud offering but seems its just the latter?

I assumed they were open source but now that I checked they are not, they say "Open" because they route to third-party open models. Yikes. Another VC crap layer?

Re: OpenRouter raises $113M Series B

#29

Post by zorked »

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…

The way how you manage the caps in OpenRouter is how every metered API provider should do it: keys have limits, and you can change the limits, and you set the limits to refill periodically, and you can create as many keys as you want.
Post reply on HN