[wiether]

People may feel differently about the fee that OpenRouter takes, but I think the service they provide is worth the extra cost.

Having access to dozens of models through a single API key, tracking cost of each request, being able to run the same request on different models and comparing their results next to each other, separating usages through different API keys, adding your own presets, setting your routing rules...

And once you start using an account with multiple users, it's even more useful to have all those features!

Not relying on a subscription and having the right to do exactly what you want with your API key (using it with any tool/harness...) is also a big plus to me.

[therealpygon]

I agree with you in certain circumstances, but not really for internal user inference. OpenRouter is great if you need to maintain uptime, but for basic usage (chat/coding/self-agents) you can do all of what you mentioned and more with a LiteLLM instance. The number of companies that send a bill is rarely a concern when it comes to “is work getting done”, but I agree with you that minimizing user friction is best.

For general use, I personally don’t see much justification as to why I would want to pay a per-token fee just to not create a few accounts with my trusted providers and add them to an instance for users. It is transparent to users beyond them having a single internal API key (or multiple if you want to track specific app usage) for all the models they have access to, with limits and logging. They wouldn’t even need to know what provider is hosting the model and the underlying provider could be swapped without users knowing.

It is certainly easier to pay a fee per token on a small scale and not have to run an instance, so less technical users could definitely find advantage in just sticking with OpenRouter.

[BeetleB]

The two things I like about OpenRouter:

1. The LLM provider doesn't know it's you (unless you have personally identifiable information in your queries). If N people are accessing GPT-5.x using OpenRouter, OpenAI can't distinguish the people. It doesn't know if 1 person made all those requests, or N.

2. The ability to ensure your traffic is routed only to providers that claim not to log your inputs (not even for security purposes): https://openrouter.ai/docs/guides/routing/provider-selection...

It's been forever since I played with LiteLLM. Can I get these with it?

[napoleond]

> It doesn't know if 1 person made all those requests, or N.

FWIW this is highly unlikely to be true.

It's true that the upstream provider won't know it's _you_ per se, but most LLM providers strongly encourage proxies like OpenRouter to distinguish between downstream clients for security and performance reasons.

For example:

- https://developers.openai.com/api/docs/guides/safety-best-pr...

- https://developers.openai.com/api/docs/guides/prompt-caching...

[BeetleB]

Fair point. Would be good to hear from OpenRouter folks on how they handle the safety identifier.

For prompt caching, they already say they permit it, and do not consider it "logging" (i.e. if you have zero retention turned on, it will still go to providers who do prompt caching).

[Deathmax]

OpenRouter tells you if they submit with your user ID or anonymously if you hover over one of the icons on the provider, eg OpenAI has "OpenRouter submits API requests to this provider with an anonymous user ID.", Azure OpenAI on the other hand has "OpenRouter submits API requests to this provider anonymously.".

[BeetleB]

But does "anonymous user ID" mean that they make a user ID for you, and it's sticky? If I make a request today and another tomorrow, the same anonymous user ID is sent each time? Or do they keep changing it?

[therealpygon]

1 - I can’t speak to whether that is the case with OpenRouter. However, I suspect that there is more than enough fingerprint and uniqueness inherent to the requests that an AI could probably do a fairly accurate job of reconstructing “possible” sources, even with such anonymity. The result is the same, all your information is still tied to OpenRouter in order to track the billing. That also ignores that OpenRouter is also privy to all that same information. In the end, it comes down to how much you trust your partners.

As for LiteLLM, the company you would pay for inference is going to know it is “you” — the account — but LiteLLM would also have the same effect of appearing to be a single source to that provider. That said, a uniqueness for a user may be passed (as is often with OpenRouter also) for security. Only you know who the users are, that never has to leave your network if you don’t want.

2 - well, you select the providers, so that’s pretty much on you? :-) basically, you are establishing accounts with the inference providers you trust. Bedrock has ZDR, SOC, HIPPA, etc available, even for token inference, as an example. Cost is higher without cache, but you can’t have true ZDR and Cache (that I know of), because a cache would have to be stored between requests. The closest you could get there is maybe a secure inference container but that piles on the cost. Still, plenty of providers with ZDR policies.

LiteLLM is effectively just a proxy for whatever supported (or OpenAI, Anthropic, etc compatible api provider) you choose.

[instalabsai]

One additional major benefit of OpenRouter is that there is no rate limiting. This is the primary reason why we went with OpenRouter because of the tight rate limiting with the native providers.

[BeetleB]

I think it's more accurate to say that they switch providers when there is rate limiting.

The underlying provider can still limit rates. What Openrouter provides is automatic switching between providers for the same model.

(I could be wrong.)

[Computer0]

Beyond that, with some providers like Open AI, API limits are determined via a tiered account system based on your business relationship and spend.

[cjonas]

Wouldn't they be using the Azure inference API or AWS bedrock on their own accounts and NOT be going through the openAI/Anthropics servers anyways? I just always assumed this is how the big inference "resellers" (openrouter, cursor, etc) were operating.

[wongarsu]

A lot of inference providers for open models only accept prepaid payments, and managing multiple of those accounts is kind of cumbersome. I could limit myself to a smaller set of providers, but then I'm probably overpaying by more than the 5.5% fee

If you're only using flagship model providers then openrouter's value add is a lot more limited

[rvnx]

The main thing about Openrouter is also that they take 100% of the risk in case of overcharges from the models, you have an actual hard cap.

The minus is that context caching is only moderately working at best, rendering all savings nearly useless.

[largbae]

I haven't noticed any problems with large context requests through OR to e.g. Opus (other than the rate at which my budget gets spent!). Is this a performance thing?

[SR2Z]

Is there any risk? Don't the model providers also bill by the token?

[fuzzy2]

The accounting could be asynchronous, so you could overshoot your budget by a few requests before you're blocked.

[fg137]

> The number of companies that send a bill is rarely a concern

Not true in any non startup where there is an actual finance department

[datadrivenangel]

LiteLLM had a major security incident recently, and often isn't actually that useful an abstraction...

[cobertos]

Does OpenRouter perform better than LiteLLM on integration though? I found using Anthropic's models through a LiteLLM-laundered OpenAI-style API to perform noticably worse than using Anthropic's API directly. So I've scrapped considering LiteLLM as an option. It's also just a buggy mess from trying to use their MCP server. The errors it puts out are meaningless, and the UI behaves oddly even in the happy path (error message colored green with Success: prepended).

But if OpenRouter does better (even though it's the same sort of API layer) maybe it's worth it?

[blazarquasar]

OpenRouter performs much, much better than LiteLLM proxy. In my experience, if OpenRouter offers a model, the API will be supported. They also often have inference providers available that will perform much better than the default provider. Just as an example, Z.ai is sitting at around 10 token/s for GLM 5.1 while friendly is doing 70 token/s for the same model through OpenRouter.

LiteLLM proxy also adds quite some overhead as well.

I have personally settled on a mix of Bifrost as my router which connects to OpenRouter or some other providers that I deem more privacy friendly.

[vidarh]

I love Openrouter. The ability to define presets, and the ease of access is well worth the few vs. juggling lots of providers separately. I maintain a few subscriptions too - including the most expensive Claude subscription - but Openrouter handles the rest for me.

[r0fl]

Love openrouter I can use cheap models without having to have an api at a bunch of different providers and can use the expensive models when im in a pinch and am maxed out from claude or codex

well worth the 5% they take

[spaniard89277]

You can get the same with kilo gateway without the fee.

[abdusco]

If you want to try a model quickly, you'll have to pay the original provider at least 5 USD. With OpenRouter, you can pay pennies. If you decide it's not for you, then you don't have to leave the rest of your deposit with the provider.

[muyuu]

Have you tried Kilo? I'd like to hear from someone who has tried both to know how do they compare.

[wiether]

I went on Kilo's website and it's seems to be closing doors on what I'm already doing.

My coding is done with OpenCode with an OpenRouter API Key.

Going with KiloCode would be doing the same, but with some more layers.

And given that I can't see the on-demand API pricing, I'm really not convinced on how it would be an improvement.

[_s_a_m_]

Doesnt Copilot Pro+ does the same?

[windexh8er]

Not even remotely close.

[sandos]

It does have multiple suppliers of models at least?

[_s_a_m_]

By default is has already all OpenAI and Anthropic models

[pixel_popping]

Expect you don't have the right to do what you want with the API Key (see waves of ban lately, many SaaS services have closed because of it).

[embedding-shape]

Unless you provide some more details, at least outline what "do what you want" was in your case, this seems like just straight up FUD.

[himata4113]

openrouter accepts crypto so might have been some money laundering involved for reselling dirty crypto for llm api.

if that wasn't the reason, hey that's actually a great way to launder money (not financial advice).

[embedding-shape]

So you pay OpenRouter with cryptocurrencies, which they accept as a payment method, and then what, they block your account because the cryptocurrencies you paid with came from some account on the blockchain associated with other stuff?

Or what are you really saying here? I don't understand how that's related to "you don't have the right to do what you want with the API Key", which is the FUD part.

[himata4113]

You pay openrouter with dirty crypto, then you have a business which simply resells openrouter giving you clean fiat. I think openrouter specifically only banned those kind of accounts since that's what I have observed from other comments / research. numlocked in this thread has explicitely said that they don't ban accounts for any of the reasons specified above which narrows down the scope to some form of broken ToS specifically around fraud and money laundering.

[embedding-shape]

And then you go on HN and post "you don't have the right to do what you want"? Yeah, FUD and good riddance if so.