RussianCow

> It is, but isn’t it all warranty in your scenario?

There are numerous recent stories of companies refusing to make good on their warranties and instead offering customers a refund for the original price paid. One example: https://www.tomshardware.com/pc-components/hdds/toshiba-refu...

Because the end goal is to ban non-US AI companies from being able to do business in the US.

For caching, only if you don't specify your preferred providers and let OpenRouter route each request itself. I have stuff like this in my OpenCode config for each model I use and I regularly get ~90-95% cache hit rates.

    "order": ["relace", "coreweave", "novita", "baseten", "together"],
    "allow_fallbacks": false

It still won't be quite as high as you'd get by just using DeepSeek because occasionally a request will fail and you'll get routed to a backup provider with nothing cached, but it's close enough not to matter in most instances.

But I can't argue with the lower off-peak pricing when using DeepSeek directly. The downside is they train their models on your input, which might be a deal-breaker for many users (as it is for me).

Honestly, I know several devs who do chores around the house or even play video games while AI does the bulk of the heavy lifting. If nobody cares or even realizes, does it matter? (To be clear, they all work remotely.)

Which doesn't matter if they're still not profitable.

I don't see any kind of input cache discount listed on your pricing page. Do you offer that, or is all input priced the same?

The issue is that all input (including context) counts towards that limit. So 10 requests with 50k of context will blow through the limit, even if little to no output was generated, which is incredibly easy to do with agentic workloads.

This is pretty terrible advice when there are dozens of AI inference providers out there serving great models with significantly more cost effectiveness than you'd get from buying your own hardware.

I don't trust any company with their word on anything. Luckily, privacy policies are legally binding.

Presumably the number that OpenRouter shows is averaged across all requests.

Most providers do what's called "prefix caching", where each turn in a session is cached such that sending new messages with the exact same "prefix" (set of previous messages) gives you the cache read price on that input instead of the full price. As long as you're not changing your system prompt, available tools, etc mid-session, you automatically benefit from this.

They're not "docking points", they're calculating it in the most straightforward way. If I start a session and the majority of requests are sent to Provider A, and my last request gets routed to Provider B, I have a 0% cache hit rate with Provider B. I'm very curious how else you expect this to be calculated? Do you think they're completely omitting requests that switch providers mid-session?

FWIW, I get significantly higher than listed cache hit rates when I pin my session to a specific provider, which is further evidence of the above.

But presumably everyone in your company/team is using Jira, so it's not an "ad" because it's a product already used internally. Claude is appending these links to all commits by default, whether or not others on the team use Claude. Those are very different things.

How else would you expect them to calculate it?

This is very much NOT my experience in practice, even though it's how I would expect it to work. OpenRouter will happily bounce you between several providers (none of which have downtime) even within the same session. Requesting specific providers is the only way I've been able to hit a cache rate above 90%.

Can you give some examples of where it matters? I'm genuinely curious.

That explains the difference, but what's the purpose?

Interesting. I wonder where they're getting their data from then, because they list Z.ai under Singapore, but everything I'm finding says they're based in Beijing. Same with MiniMax.

I don't think that's right, or if it is, OpenRouter has incorrect data. Several Chinese companies (headquartered in China) have Singapore listed as their region on OR. And some companies, like Alibaba Cloud, have multiple regions listed.

I'm happy to be proven wrong, but this makes me think that the region is where the servers are, not where the HQ is.

If you click on the provider name, the panel that pops up shows a "Region" value. Not every provider lists their region, however.

You might be joking, but a harness provides much more than just the prompts: at a minimum, it provides the system prompt and the built-in tools that the LLM can use, but it can also provide things like subagent management, custom compaction logic, session forking, etc.

I think it also helps that it's basically the default platform for any software that AI writes, unless you tell it otherwise. And JavaScript is one of the most widely used and well known languages in the world, so there's that, too.

> A difference in degree

But a pretty huge difference. It's the difference between a few individuals throwing waste into a river vs a corporation systemically polluting it. Surely one is more of a problem than the other?

Someone brings this up on just about every AI-related thread. I think it's nonsense. Nobody wants to maintain a fork of any remotely complex software, not even with AI. And in a corporate setting, nobody wants to use your custom fork; they just want to use the standard software they already know with the quirks they've already learned.

That likely isn't as relevant for on-device iPhone usage as it is for Real Work™. I won't notice the difference between 50tps and 1000tps when asking Siri a question.

There's no reason you couldn't present a GUI over an SSH connection. Whether the agent is running locally or remotely is orthogonal to the type of interface used.

I'm not confusing anything since you can't use custom harnesses with your Claude subscription—you have to use Claude Code. So as far as the Claude sub is concerned, the models and the harness are coupled.

They're not as good. I've tried all the options available a couple months ago, and none of them feel nearly as polished as Cursor. For one thing, Cursor Tab is just far better than any other "next edit" prediction I've used. I also happen to like their agent UI the most, but they don't support ACP, so you can't use it with Claude Code, which was a deal-breaker for me.

These days I've switched to Zed, which is good enough (and wicked fast), but I still miss Cursor as an IDE.

> the results are much better than clowning on bloated CC.

I won't argue with the cost effectiveness, but the results are very much not better. Opus and Fable are in a different league than DS4 Flash. Even GPT Terra, which I really like overall, sometimes gets stuck in weird loops and starts to do stupid stuff once its context window fills up. Whereas I can more or less trust the big models to just Do The Thing™ on the first try.

With that said, you get way more value out of a GPT subscription than you do from Claude, partly because of the ability to use more efficient harnesses.

The problem is that companies tend to exaggerate their own scale and think they need k8s and dedicated infra people when they could get by with a handful of beefy VMs or dedicated servers.