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

61–70 of 279 posts

Re: OpenRouter raises $113M Series B

#61

Post by ajyoon »

enraged_camel wrote: post #36
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…

>> 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 Why not... Cursor?

Cursor's coverage on open weight models is very minimal, and it's irrelevant for testing models in your actual application.

Re: OpenRouter raises $113M Series B

#62

Post by willis936 »

croes wrote: post #32

Aren’t they totally dependent on the good will of the model providers?

In what way? They're just an API customer like any other and charge a bit more on top. Providers would have to carve out their usage terms to not allow resell, which does nothing besides lose customers to competitors. If they all did that then you would tap on the FTC's shoulder and suggest they do their job.

Re: OpenRouter raises $113M Series B

#63

Post by gbro3n »

derefr wrote: post #43
Aurornis wrote: post #14

Earlier quoted context omitted.

Good points. The easy experimentation factor is helpful for development, though I would gently encourage everyone to migrate to the 1st party APIs for pricing at scale. OpenRouter is also a good place to find free LLM access with a catch: You should expect that any inputs and outputs are going into someone's training database. Clearly anyone who can pay should be using paid models with privacy protections, but the fr…

> You should expect that any inputs and outputs are going into someone's training database. True enough, in theory; but what exactly are you imagining would be a useful-enough signal in the OpenRouter request+response stream, that any company would want their data as training material? Even a single OpenRouter-API-key-identified subscriber's traffic, may consist of an mixture of traffic from multiple different sessio…

I've wondered this too - exactly how are our inputs and outputs useful as training data? So I asked Gemini. Apparently using negative sentiment in user or llm responses can serve as RLHF, and the human prompts can also serve as useful data for what problems the llms need to be able to solve. There's also that smaller models can train on and improve from data from larger models but that's less relevant when not switching models in context.

Re: OpenRouter raises $113M Series B

#64

Post by gnulinux »

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

Thank you so much for this! I've been working on exactly this problem this week (which OpenRouter providers have the highest cache rate on average) because cache cost is sometimes half your cost: I'd much rather use a provider with more input caching with a more expensive/better LLM. Your results and lists seem more comprehensive than what I've done so far. Very helpful!

Re: OpenRouter raises $113M Series B

#65

Post by 827a »

enraged_camel wrote: post #36
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…

>> 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 Why not... Cursor?

Cursor only supports a single model (Kimi K2.5) not made by the Big 4 labs (OpenAI, Anthropic, Google, xAI). Cursor is actually extremely bad at wide model support.

OpenCode is much better at it.

Re: OpenRouter raises $113M Series B

#66

Post by largbae »

enraged_camel wrote: post #36
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…

>> 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 Why not... Cursor?

I use Cursor with OpenRouter for some projects and it's great. Most of the time I just use Auto and let Cursor use its model or choose. If I run out of quota, or I'm not getting what I want, I switch off Auto and use OpenRouter to pick Opus, Codex, or whoever(all are available). Can continue the same context if you want, type "please continue" in the agent prompt, and on you go.

Re: OpenRouter raises $113M Series B

#67

Post by zenoprax »

fontain wrote: post #12
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…

Out of interest, why OpenRouter over a free option like Cloudflare’s AI gateway or another paid option like Vercel’s — any specific benefit to OpenRouter you’ve found, or just first you used that’s good enough?

I didn't know about these options either. I am using Cline: Cloudflare isn't an option but Vercel is. My spending is pretty low overall now that I'm using local models much more but good to know that there are cheaper alternatives to try or at least suggest to others.

Other features I've just noticed: - configurable prompt injection protection using OWASP regex (https://cheatsheetseries.owasp.org/cheatsheets/LLM_Prompt_In...) - configurable PIM protection for outbound prompts - input/output logging - "JSON healing" to auto-correct minor hallucinations

Lots of other stuff too. The business model seems pretty simple and the value-add features don't look particularly expensive or difficult to copy.

Re: OpenRouter raises $113M Series B

#68

Post by squeaky-clean »

srameshc wrote: post #31
totaa wrote: post #19

Earlier quoted context omitted.

Google Vertex

https://aistudio.google.com/spend ? Monthly spend cap

> Long-running tasks like batch mode completions and agent sessions may incur overages beyond your project spend cap.

> Billing data processing times can be delayed in AI Studio, up to around 10 minutes. You may experience overages beyond your project cap if billing data hasn't processed before more charges are accrued.

https://ai.google.dev/gemini-api/docs/billing#project-spend-...

That's a soft cap, not a hard cap

Re: OpenRouter raises $113M Series B

#69

Post by zenoprax »

enraged_camel wrote: post #36
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…

>> 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 Why not... Cursor?

Cursor has limits even when using your own key. I was even cut off using a local model. I guess they use some sort of harness that requires non-local resources? I'm not sure I've actually tried to use Cursor in a fully-offline scenario yet. Cline works well enough and doesn't require any sign-up.

Re: OpenRouter raises $113M Series B

#70

Post by dvratil »

One thing I haven't seen mentioned here yet and really like about OpenRouter is their openrouter "meta" model, that automatically routes the prompt to an appropriately capable model. Saves me a ton of money on not routing everything through Opus, but not giving me bad results when I ask something more complex, which gets autorouted to Opus.
Post reply on HN