151–160 of 208 posts
Earlier quoted context omitted.
What are your plans to improve a substantial lack of customer support? https://news.ycombinator.com/item?id=49577159
Hmm, let me check. That certainly seems wrong. Can you send me an email w/ your email so I can look into it? im cc at openrouter.ai. Or DM me on X? x.com/cclark
I still don't get the appeal of OpenRouter. Why not just generate API keys from the providers you want to use, which should not exceed 3-4, I assume, and integrate them into your apps to call them? Are people so lazy, or am I missing something?
If you're making a commercial SaaS, that's probably the way to go. For individual users like me, with a coding harness and some extra BYOK tools, OpenRouter is convenient and the few extra percent don't hurt much. I appreciate being able to try out any new model with just an ID swap, same with inference providers when they prices change. I know I wouldn't enjoy managing 5+ accounts, each with their own balance, in 3+…
Earlier quoted context omitted.
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.
> The same model will benchmark very differently Providers probably serve quantized versions without disclosing it. Which is a real shame, because for certain tasks I would be perfectly willing to trade accuracy for cost. But, unfortunately, it is impossible to explicitly choose how quantized do you want your model to be, unless you are running it yourself on your own (or rented) hardware. BTW, does anyone knows if L…
I mean that is addressed as well later, even when they do declare the quantization, doesn't mean you'll get better performance than the lower quantized one. I'm guessing they're doing something similar to what stadia was doing, saying you are playing games in 4k, because you're getting a 4k stream, but the game itself is running in 1080p
Earlier quoted context omitted.
> vendor-neutral slop Never before have I heard this sentiment, NGL. Vendor-neutrality has been an OS(/FLOSS) darling for, well, the whole time. RE:"single vendor", if this post is to believed then you might have picked one that has 100x the tool calling errors for the next SoTA model, if your single vendor serves the next SoTA in the first place. It also completely erases the notion of competition driving down price…
How does it erase the notion of competition driving down prices? Endpoints are largely compatible, so the code change required to switch from one to another is trivial. Don't load 6 months' worth of credit in an account, keep it tight. There's fairly little lock-in. The most significant lock-in to me isn't even something you mentioned, but rather it's model related; I personally put a little time into trying to optim…
Wrapping a specific implementation in a neutral function is something you learn to do in year 1 of programming.
This specific issue and argument I see in lots of different aggregator dependencies, Terraform, LiteLLM/OpenRouter.
They promise to save some hypothetical work in the future if your boss asks to change vendors, and it turns out to be very trivial work that is just a regular part of our programming job, changing a couple of lines in order to change vendor.
It's worth noting that there exists a similar set of technologies with a reasonable tradeoff, using a framework that targets different user-platforms makes sense, write-once and deploy at iOS and Android is a reasonable tradeoff, but because you are deploying to those providers simultaneously and it's a user-choice so you don't get to pick one or the other (without losing clients), there's still arguments to chosing just one and losing market share, or doubling the workload and building native for both, but this is a true engineering choice. I feel like stuff like OpenRouter and TerraForm take elements of these frontend abstraction technologies and wastefully apply them to backend tech.
A particularly egregious case is when there's an aggregation layer for aggregation layers, say, a tool that generates TerraForm or Chef configs, or a tool that generates Docker and Podman containers, or a tool that generates LiteLLM/OpenRouter configs. Sounds dumb, but it happens when there's a market share for it. Can even get to 3 layers deep.
At the foundation might be an aversion to making an irreversible choice, which is an innate emergent psychological phenomenon, but is supported by the Bezos Amazon policy of reversible and irreversible doors. But again, even if you want to be light, using some of these aggregating tools isn't necessary, you can just build on top of a tech, and switch later. The only thing you get with an aggregating layer is that the API ends up being the common denominator so you lose out on the competitive advantages of each choice, or are forced to use even more complex API logic like LLM(commonParam1, commonParam2, vendorParams= {"vendor1"=:{"vendorParam1":"blabla"}} or worse, use hard-coded aggregator provided mappings between the aggregator API and the vendor API that may be incomplete and relies on updates from the aggregator dev.
Less is more.
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 “Ope…
> The same model will benchmark very differently Providers probably serve quantized versions without disclosing it. Which is a real shame, because for certain tasks I would be perfectly willing to trade accuracy for cost. But, unfortunately, it is impossible to explicitly choose how quantized do you want your model to be, unless you are running it yourself on your own (or rented) hardware. BTW, does anyone knows if L…
In my coding agent harness I've included 25 open weight providers mainly because I keep having to find new ones when what was previously a great combination of model and provider becomes pretty bad. vllm has defect that causes reasoning to get dropped much of the time for the GLM family of models. sglang has a defect that causes the elements of array args to get dropped for the deepseek family of models. Some providers need some very specific additional config passed through for reasoning to make it back to the model.
I've not tried OpenRouter as adding yet another layer will just make it that much more difficult to get a model and provider combination working well.
I suspect people's bad experiences with open weight models have a lot to do with these headaches. Finding a good model and provider combination is pretty tedious and so far its been a never ending process. I'd really like to host my own models but it isn't economically feasible for one person for the open weight models that work well (i.e. the 300B+ ones).
Earlier quoted context omitted.
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…
> 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…
My basics are I have a test suite that: 1. Finds newest models of my versions 2. Inferences every single model and a few providers for each with a short problem 3. Analyze latency and if a model failed the stupid simple questions drop it and the provider 4. Run larger context haystack kinds of problems.
It's cheap and fast less than 5$ so I can do this daily, hourly, whatever depending on how much I care. If it's mission critical I would say you need a two day study running once an hour to know the STD of model variance.
Then lock a top 3 contenders via latency dropping routing.
Is this easy? No. Is it cheap? Also no. Is it better than just using a trusted labs api? Also not really.
But it does give you exponentially more flexibility. Being able to run 10 unique models at the flick of a switch on a problem for pareto front analysis is amazing. And giving a dropdown for customers for multiple model options is powerful.
That looks absolutely horrifying. What are the alternatives ??
Just use a single vendor. Literally nothing wrong with that, and you avoid the complexity of both n-1 of the vendors (leaving you with the highest quality vendor) as well as the issues with the aggregating layer. Not sure why people are drawn to this particular blunder. The promise of vendor neutrality maybe? I'll take working product over vendor-neutral slop anyways.
That's a serious questions that I really interested in the answer too. I have 25 providers included into my coding agent harness not because I care about vendor neutrality, but because I have to keep adding new ones as inference quality degrades at the providers I was using. Its quite tiresome.