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 Claude Opus with OpenRouter because that 5% surcharge is meaningful at that level of cost instead of going with the source API providers. But people are clearly doing it, and it's pure revenue.
IDK, but that sounds like something that would be better implemented with an open-source library to which providers supply support patches. Why do I need a company to act as a proxy and not just run a relatively simple shim layer on my machine?
I'm just a stupid systems programmer working in the bowels of AI and I understand there is a lot of seemingly pointless software which exists solely to provide a slight boost to convenience in exchange for money. Is OpenRouter just that? Do they actually host models themselves or centralize billing amongst various providers?
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 it's very useful to have hard limits so it doesn't cost you $1m overnight because someone started abusing it.
3. Their rankings are one of the more interesting signals for which models are popular, despite their flaws (most OpenAI and Anthropic users don't go via OpenRouter, it's currently not possible to tell the difference between many users switching v.s. one "whale" changing their preferred model)
Given how API costs are becoming meaningful for a lot of companies now, having a provider like OpenRouter to help measure your spend and easily experiment with and switch providers feels like a valuable service.
The main friction reduction, for me at least, is the consolidated billing that avoids extra bureaucracy in corporate environments. The API-translation/abstraction tends to cause more problems than it solves.
I’d prefer something that consolidates billing, but still lets me use providers' APIs directly (or via some "raw HTTP" proxy). There are plenty of unified API gateways, but I haven’t seen one that is just billing/auth in front of the native provider APIs.
They also do a good job working over the little differences between APIs. Tool calling sometimes breaks on major providers, and OR will patch it before the provider does. Libraries like LiteLLM do this too, but OR is faster.
Did you know that if you put some money into your OpenAI account it expires after a year? I was very annoyed when that happened, no refund no warning it’s just gone as if it was a promo credit.
Openrouter is very nice since it puts a barrier between you and those suppliers that were supposed to be like utilities. I got the feeling that if OpenAI was left alone they would be nice as a telco.
Unfortunately the model companies will simply reinject the friction by mandating BYOK (Bring Your Own Key -- i.e. the end user must onboard with each model company individually).
It's not just comparing all the models, it's also comparing all the providers and configurations of those models.
If you're doing any kind of production AI work you'll end up with outages caused by calling a single provider, OpenRouter seamlessly switching between providers is a godsend for uptime.
But even more than that there's meaningful cost+speed differences.
Here's Sonnet 4.6 being served direct, via Amazon and via Google
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?
An amazing service. I use its 20+ free LLM options to allow completely free usage of LibreOffice AI extension with no signup https://librethinker.com .
I was sort of hoping that they were bootstrapped or at least non-VC funded. I'm wary of them introducing consumer-unfriendly revenue-generating schemes.
OpenRouter’s biggest value to me is reducing switching costs between models. The markup matters at scale, but for exploration and early-stage development, the convenience is hard to beat.
> ... 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.
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.
One thing that OpenRouter makes easy is the ability to manage API keys (mint new ones, expiry/limits per key, etc.) that I wish that other providers would make possible/easier.
So many use cases, like sharing AI/assisted features externally, with the ability to use those features but also limit the fallout if its shared / used for other purposes, without jumping through more fallible hoops like safeguards etc.
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 system in place, albeit the dev and maintenance cost and of setting up such an “LLM gateway” could be significantly reduced with OpenRouter. I feel that this is largely an ignored, forgotten part of operating GenAI apps at scale.
OpenRouter is our primary provider for evaluation data, and we've been really happy with them!
I'm sure they're experiencing growing pains, but a larger model selection (and faster releases for open weights models), would keep us from using other providers. For example, it took much longer than it should have to get Qwen 3.6 ~30B class models released (almost 2 weeks if I recall)
I like OpenRouter - lets me test out new model quickly and easily. I would still need a good functioning mobile application for it.
I think they should go in this direction: they should make their own Model Agnostic versions of whatever functionalities other AI companies are making. Examples
1. personal chat app
2. the chat app working with their own implementation of memory
3. coding harnesses that are model agnostic
When I think of OpenRouter, I should think of "model agnostic LLM tools".
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.
I'm reading the website and nothing about this addresses the compute running the models. If that's going to a third party (just like openrouter is), then there are no guarantees, other than words on paper.
81 comments
[ 2.4 ms ] story [ 66.4 ms ] threadThat said, I don't understand the people who use something a full agentic backbone with expensive models like Claude Opus with OpenRouter because that 5% surcharge is meaningful at that level of cost instead of going with the source API providers. But people are clearly doing it, and it's pure revenue.
I'm just a stupid systems programmer working in the bowels of AI and I understand there is a lot of seemingly pointless software which exists solely to provide a slight boost to convenience in exchange for money. Is OpenRouter just that? Do they actually host models themselves or centralize billing amongst various providers?
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 it's very useful to have hard limits so it doesn't cost you $1m overnight because someone started abusing it.
3. Their rankings are one of the more interesting signals for which models are popular, despite their flaws (most OpenAI and Anthropic users don't go via OpenRouter, it's currently not possible to tell the difference between many users switching v.s. one "whale" changing their preferred model)
Given how API costs are becoming meaningful for a lot of companies now, having a provider like OpenRouter to help measure your spend and easily experiment with and switch providers feels like a valuable service.
I’d prefer something that consolidates billing, but still lets me use providers' APIs directly (or via some "raw HTTP" proxy). There are plenty of unified API gateways, but I haven’t seen one that is just billing/auth in front of the native provider APIs.
Openrouter is very nice since it puts a barrier between you and those suppliers that were supposed to be like utilities. I got the feeling that if OpenAI was left alone they would be nice as a telco.
OpenAI and Anthropic have already done this.
Mandated BYOK will sink OpenRouter.
If you're doing any kind of production AI work you'll end up with outages caused by calling a single provider, OpenRouter seamlessly switching between providers is a godsend for uptime.
But even more than that there's meaningful cost+speed differences.
Here's Sonnet 4.6 being served direct, via Amazon and via Google
https://la9q13gg8w.evvl.io/
(spoiler: Google was both fastest and cheapest)
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.
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.
So many use cases, like sharing AI/assisted features externally, with the ability to use those features but also limit the fallout if its shared / used for other purposes, without jumping through more fallible hoops like safeguards etc.
I'm sure they're experiencing growing pains, but a larger model selection (and faster releases for open weights models), would keep us from using other providers. For example, it took much longer than it should have to get Qwen 3.6 ~30B class models released (almost 2 weeks if I recall)
I think they should go in this direction: they should make their own Model Agnostic versions of whatever functionalities other AI companies are making. Examples
1. personal chat app
2. the chat app working with their own implementation of memory
3. coding harnesses that are model agnostic
When I think of OpenRouter, I should think of "model agnostic LLM tools".