41–50 of 279 posts
Earlier quoted context omitted.
OpenRouter is merely only a proxy. They also host some open-weight models
I don't think they do. They proxy to a bunch of open-weight model hosts, but I've not seen that they host them themselves. They don't list themselves on https://openrouter.ai/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…
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…
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 sessions, under potentially multiple different end-users. (Where, if the subscriber is doing security correctly, then their OpenRouter key lives on a gateway rather than in a frontend app; and so the only IP address / UA / etc OpenRouter sees is that of the gateway itself.)
And the traffic stream may also invoke multiple models, and provide multiple different system prompts for those models; which, while marked in the traffic (i.e. conveyed as part of each request), makes the resulting data much less useful in aggregate, than if it were all training data for one model with one system prompt.
Plus, there are no RLHF signals in OpenRouter data. Even if OpenRouter wanted to build a general model-neutral framework for collecting RLHF-type data, it can't force subscriber apps to do the UI-level stuff necessary to collect it (i.e. the things ChatGPT/Claude do, with "thumbs-down" buttons, A/B tested responses, etc.) Analysis would have to rely on pure transcript-level user sentiment extraction.
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.
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…
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…
Earlier quoted context omitted.
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'll be honest, I hadn't clocked that Cloudflare and Vercel were offering equivalent products. Looks like Vercel even have their own leaderboard: https://vercel.com/ai-gateway/leaderboards/models Surprising that they have Opus 4.8 and 4.6 listed on the leaderboard but not Opus 4.7.
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…
It’s interesting all the focus on opt-out from training. Sometimes I worry there is an intentional focus on that so people don’t think about the other ways the company might be profiting off our data. Like I pay for Anthropic and they don’t train on that but are they selling my “anonymized” usage data in some other way?
Earlier quoted context omitted.
Both OpenAI and Anthropic have billing caps… who doesn’t?
Based on experience, Google Cloud. No idea if that translates to Gemini usage billing.
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 .
The handful of times I did try a free model is when I used their chat interface to quickly compare a few open weight models with a single prompt. That's the only usage I can think which could have triggered the block on my account. Even still, what's the point in have the simultaneous chat feature if using it veers so quickly into a ToS violation.
Their support is beyond useless in helping understand the situation. I don't think I managed to speak to anyone other than Tony Bot (or whatever it was named).
Edit:
Total usage over 1 year:
Claude Sonnet 4.6 $8.80
Gemini 3.1 Pro Preview $6.71
Claude Opus 4 $6.19
Claude Opus 4.1 $7.49
Gemini 2.5 Pro $10.06
Claude Sonnet 4.5 $12.74
GPT-5 Codex $2.56
Grok 4 $4.39
Gemini 2.5 Flash Image Preview (Nano Banana) $1.88
GPT-5 $7.30
Others $7.99
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…