Hacker News Reader

Comment by joshstrange | Hacker News Reader

This squares with my, much much, smaller OpenRouter usage. It’s just incredibly unreliable and you are forced to pin providers and even then it can be a crapshoot as the author found.

OpenRouter sells the idea of swapping being commodity providers but it couldn’t be further from the truth. Provider A is often not swappable for B or C (again, as this author found). It can be crazy-making as you sit there thinking “OpenRouter has no clothes right?! Am I the one that’s wrong?”.

I love the _idea_ of OpenRouter and maybe Stripe can improve this situation but the only sane way I’ve found to use it is to tightly pin providers to the point I wonder if I should just use the providers directly.

Without pinning you are in for a world of hurt and unreliability (varying model capabilities, speed, etc).

View on HN

> just incredibly unreliable and you are forced to pin providers and even then it can be a crapshoot as the author found.

But that's the intention right? Even the name implies they just send stuff around for you, and if you want to control the routing, you'd lock down providers. I don't see how they could build what they wanted to build, and not have it end up unreliable if you freely round-robin between providers, it's bound to work exactly like this.

> I love the _idea_ of OpenRouter and maybe Stripe can improve this situation but the only sane way I’ve found to use it is to tightly pin providers to the point I wonder if I should just use the providers directly.

This is quite literally the point of OpenRouter. A unified interface, so you can easily switch providers without changing a ton of code which using providers directly would most likely mean, as there are slight differences between them. And the providers all run different weights, so of course quality/performance will differ among them.

I guess OpenRouter is a bit like Amazon, in that they're just routing stuff around for you, but to actually find the good and usable stuff, you need to focus in on what providers/manufacturers you know are good, and stick with those. Still, the unified interface helps you to shop around and try different ones when you want to.

  if you want to control the routing, you'd lock down providers

I don't want to control routing. I want the model to work how the giant, prominent "BENCHMARKS" section says it works, not randomly have a 100x error rate.

If OpenRouter is a marketplace to pick a provider while avoiding huge problems, it is terrible at that job. It surfaces literally none of that info in the top-level list, the graphs below are mislabeled and useless at best, and doesn't notify you of this horrifying situation anywhere, even in passing. There's not even a way to compare providers, AFAICT -- you can only compare models.

  This is quite literally the point of OpenRouter.

Their tagline is "better prices, better uptime, no subscriptions". The first two of these directly and inherently contradict your understanding -- neither would be possible if OpenRouter was just a fancy way to change something in their GUI rather than changing the target url of your gateway.

> I don't want to control routing. I want the model to work how the giant, prominent "BENCHMARKS" section says it works, not randomly have a 100x error rate.

Why do you care about the public benchmarks at all?

The way companies and effective individual developers use OpenRouter, is that you first create your evaluation framework/benchmark, for your specific tasks and use cases, and make that real easy to run and use various models and providers with it.

Then you run this to gather data. Then you use said data to figure out what works and what the quality/cost tradeoff you want to make is. Then you lock that down in production while you keep iterating on your benchmark to make it match with real-world use cases and keep adding the new models that pop up.

I don't think anyone serious is just willy-nilly making individual requests against OpenRouter and similar platforms, get a "feel for a provider" then use only that provider. Not only would it be wildly inefficient, but also you need hard numbers to compare so you can make informed choices.

For this process and workflow, OpenRouter is great, because adding/changing providers and models is essentially changing two strings, rather than having a adapter for each platform you want to try out.

If you just want best accuracy requests from SOTA models for your agent you run locally or whatever, then don't use OpenRouter, it doesn't make much sense, but use the provider the model maker has available, as almost all of them run their own endpoints.

If openrouter is only for people who "make their own benchmark" in a mission to roll something that's usually made by scientists with large budgets, it should say so and thus fade into deserved obscurity.

  I don't think anyone serious is just willy-nilly making individual requests against OpenRouter

Despite your confidence, that is indeed the basis of this massive corporations entire business plan.

  If you just want best accuracy requests from SOTA models for your agent you run locally or whatever, then don't use OpenRoute

If OpenRouter is only for bad accuracy, they should say as much and fade into deserved obscurity.

I think you're focusing only on the general coding agent aspect of LLMs.

> If openrouter is only for people who "make their own benchmark" in a mission to roll something that's usually made by scientists with large budgets, it should say so and thus fade into deserved obscurity.

That is the way LLMs have to be used for highest reliability. While the term stochastic parrot has been co-opted by unreasonable LLM skeptics, that is indeed what LLMs are. You have to have grounded evals that check outcomes if you want to use them reliably - or a human in the loop works too.

The more general your family of tasks, the less likely you can make automated evals. So for "general" coding agents, you need a human in the loop that can verify and it's not that easy to write an eval.

But if you have specific tasks, then you can spend the time to make a eval, and then you can optimise the way you use the LLM and get extremely good success rates. It's not like it's black magic. Nor does it need large budgets.

> that is indeed the basis of this massive corporations entire business plan.

No. Individual developers using codex (for extremely underspecified general engineering) needs human in the loop, is not amenable to evals but is only a fraction of all LLM usecases.

You'd be surprised. Not enough teams still have their own evals. India[1] and the US[2] is my experience. To get many of them to understand the benefit of putting a couple of people to do data labelling and write a couple of verifiers for just a few days every few months was so difficult. Many folks have understood it all wrong and made allotments like "big model for this task" "small model for this task". Small was sometimes parameters, sometimes brand version number, or sometimes because it has "mini" in its name.

Proper LLM adoption beyond fucking around with claude code or github copilot is so low and is only going to go up as people figure it out. I also think the new cloud agents thing might accelerate adoption among these companies, since it's a bit more plug and play. But they are more likely to be stingy about it, so I'm not sure about the high margin expectations of certain model families.

[1] not witch, but BFSI. Surprisingly parts of witch companies have it down to science already, they embedded openai or anthropic or startups like devrev more than a year back.

[2] again not high fly SF companies, BFSI.

> There's not even a way to compare providers, AFAICT

That's not quite true. The only thing they don't show per-provider is benchmark data, cause I don't think they are doing continuous benchmarking of each model from each provider, as I assume they feel that's too expensive. You can see hugely detailed breakdowns for near-time metrics per provider for any model by visiting the page for that model on Openrouter. For example see the page for Qwen 3.8 27B: https://openrouter.ai/qwen/qwen3.8-27b

Some of the killer stats they show per provider:

- Pricing: Effective price accounting for cache hit rate, by provider

- Performance: Throughput in tok/s, latency, E2E latency, tool call error rate, structured output error rate, and more; all per provider.

- Uptime: You have to click on the provider to see their specific uptime, but doing so does show the last-7-days uptime, and you can click to see more.

The thing they don't show is the one we really need, especially because model providers can skimp on quality (run lower quantization, lower kv cache precision, etc) to improve their pricing and performance. I agree that it's probably too expensive to keep running the benchmark, but we need some way to hold the providers to a certain standard, otherwise every user has to discover the problems on their own.

We are doing continuous benchmarking of each endpoint, for each provider, and it is very expensive :)

No I know, I was in the GUI as I wrote that lol. As the other person said: if they vary this much in quality, not including that way above updtime and performance is absurd. What would you use a fast, always-up, broken endpoint for?

1. Yes, but if i can't rely on openrouter to route to providers to give me the best price and the best uptime across a number of providers, and it instead gives me inconsistent results, then I will not use them.

2. As long as the apis use the openai spec, it should be fine? And what makes you say the providers are using different weights? The blogpost says the exact opposite?

3. Great example, if amazon does not lead me to good products, I will stop using it, and this is why I dislike amazon. There are so many crap products, and the search seems to try to push crap products instead of what i'm actually looking for at a good price.

You take a bunch of providers with not great uptime, put them in a pool and now you get great uptime - but it doesn't work if it's at the cost of shitty performance or failing toolcalls.

> 1. Yes, but if i can't rely on openrouter to route to providers to give me the best price and the best uptime across a number of providers, and it instead gives me inconsistent results, then I will not use them.

OpenRouter does reliably route to your specified model and provider, otherwise it'd pretty much be fully broken. Parent is complaining about the auto-provider chosing, not that all providers are unreliable.

> 2. As long as the apis use the openai spec, it should be fine? And what makes you say the providers are using different weights? The blogpost says the exact opposite?

In theory, yes. In practice, no, there are differences. Ollama, llama.cpp, vLLM and SGLang all say "ChatCompletionRequest" compatible, but the devil is in the details, they don't have 100% the same request/response schema across all compatible models.

> 3. Great example, if amazon does not lead me to good products, I will stop using it, and this is why I dislike amazon. There are so many crap products, and the search seems to try to push crap products instead of what i'm actually looking for at a good price.

Yup, makes sense! If you're unable to find models when you use OpenRouter, it makes zero sense to continue to use OpenRouter.

> You take a bunch of providers with not great uptime, put them in a pool and now you get great uptime

Huh? That's not how it works or does it make sense, nor have I've seen anyone use OpenRouter like that.

> Parent is complaining about the auto-provider chosing, not that all providers are unreliable.

Parent is claiming that the choosing is unreliable. If I rely on a provider to bring me tuna to some spec, but they get it from many different fishermen, it doesn't mean that the tuna doesn't have meet the spec. The complaint is that they're given a bunch of knobs that simply don't work with providers that they could be switched to. That's like saying that I want my tunas to be 20lbs. minimum, and I get switched to a provider that doesn't weigh their tuna at all.

The choosing is all OpenRouter provides. If it doesn't do that, then what is it good for? If I have to permanently pin the one provider who doesn't ignore what I've asked, why shouldn't I just deal with them directly?

edit: it's really supposed to reduce providers to a commodity market. If you're selling e.g. produce to a commodity market, you can't just ship whatever the hell you want. You ship something indistinguishable from others, or more likely the market itself allows you to grade what you're shipping so it's put into a bin with virtually identical stuff. The customer just buys Grade B Wheat.

Doesnt have to be all providers being bad, any unreliable providers still being routed to causes big issues.

2. Not saying they dont solve a problem, but if we can't rely on the providers being routed to, i don't really care if they provide a really nice api..

3. We are not talking about models, we are talking about providers of models. Openrouter does not route to models, it routes to providers.

What do you mean? Are you saying openrouter will not route to a provider that is up, versus one that is currently down?

There’s a surprising amount of variety in between implementations of “OpenAI” endpoints.

I mean that should be their job to verify the quality of the providers they have in their platform. Then what is the 5% for?

> I guess OpenRouter is a bit like Amazon, in that they're just routing stuff around for you

This helps forecast one possible future for OpenRouter: they begin to offer in-house provision, and people begin to migrate their uses off the "marketplace" providers and onto the "fulfilled-by-us" provision.

I treat OpenRouter as a central point to access specific providers. Pinning is a given for that use case.

I’ve tried using un-pinned models and the experience is exactly as you described: Some providers are so unreliable that the majority of requests fail. Some providers do weird things like abruptly end the response (which I get billed for and have to re-submit). Some providers are clearly running heavily quantized versions of the model because their eval performance is terrible. Some providers advertise features on OpenRouter but will reject those requests when submitted to their API.

So pinning is the way to go.

What providers do you find most reliable? And is that general across models?

OpenRouter has the advantage that I can maintain a single balance across model providers so I use it for quick iteration across and then write it into my own router (required anyway since I have many on-prem models running). The portable balance is actually very useful and my credit card is in one place.

If I could pay per request without maintaining a balance or credit card out of a single wallet (using crypto or something maybe) I would happily simply write the integration myself because OR’s caching is often not as good without some hoop jumping.

Yep, I wish more people realized that OpenRouter’s sole value proposition is that they are an LLM wholesaler.

> to the point I wonder if I should just use the providers directly.

How many account credentials, balances, and tokens do you want to maintain? Even without automatic failover services such as openrouter are still incredibly useful.

Personally I pin a single vetted provider in the interest of minimizing risk.

I think Openrouter is great for quick testing, getting a "feel" for the model, or very quick integration jobs where you want to try out as many models as possible.

For truly production use cases, use Novita, Fireworks, Toghether or something of the sort.

Did you miss the part of this article where the benchmarks specifically call out Fireworks as one of the worst in their tests:

> Fireworks scored 46% on TAU, a 30 point gap

Another surprise was DigitalOcean being bottom of barrel too.

Companies are apparently willing to risk their brand name by being deceptive about these heavily quantized/flawed model-serving.

DigitalOcean (at least through OpenRouter) is pretty reliably bad in my experience. Fireworks can be great, but it depends on the model and on the day.

DigitalOcean is bad not just through OR... Direct accesss through DO gave me such a miniscule context and maximum tokens, it was pretty much unusable. So, accessing it through OpenRouter gave bigger context length, but model behaves like it was seriously damaged - tool calling was producing paths that had / replaced with some other symbols, files were not found etc., and this is just for things that errored out, I have no idea how bad reasoning was. I had to blacklist DO completely on OpenRouter.

It's not always deceptive. Bugs in inference can be very subtle (well, bugs everywhere can be subtle).

The providers should be benchmarking their offerings daily

I only use OpenRouter to benchmark models. For my production app, I have direct integrations with OpenAI, Anthropic, Google, xAI. Even just input caching is enough of a reason to do that, assuming you are trying to build the fastest and most cost-efficient product possible. I don't understand how people supposedly run production apps using OpenRouter unless those two variables somehow don't matter to them.

Not every usecase requires prompt caching, for example prompt enchantment jobs usually can't benefit from caching at all

This (by definition) the reality of every normalization/proxy layer, standard, etc. There’s always a cost for flexibility/freedom. What’s traded is when and by whom it’s paid.

You know you can define your own provider filters and orderings, right? The filters and such are not _that_ advanced, but it might do what you need if you haven't already tried that.

Reply on news.ycombinator.com