I like how they called it “ML Infrastructure” instead of “AI Datacenters”

Nothing is new, quick tunnels were launched in 2021

https://blog.cloudflare.com/quick-tunnels-anytime-anywhere/

Quick tunnels have existed since at least 2022 (when I was using them)

honestly just Bend is a great HN title, you can describe it more concretely on the homepage

Thanks for the response Chris, I couldn't make my business work without OpenRouter in the first place, so kudos

This was meant as more of a technical reference, sorry you had to wake up to a PR drill lol

No stress! My first reaction to this was OMG THIS IS AN INCREDIBLE RESOURCE!! We are 100% grateful for this sort of feedback! Here is a direct quote of what I said at 8:17am this morning when someone sent me the article and I scanned it:

  this is amazing!!
  [8:19 AM]The first obvious win is routing around providers that arent handling image inputs correctly. That should be straightforward
  [8:19 AM]The effort param stuff...I thought we had addressed that, but will dig in. This is incredible feedback
  [8:20 AM]We should hire this guy.

Our goal is to get better, fast!

Yes, you hit it on the head. It's worth it, but you have to do your own evaluation and promotion.

Example I forgot to mention: `:nitro` ranking is not the fastest, I do a round robin sampling with representative payloads to find out the fastest providers and reorder my list on the fly.

Your doing that sampling/promotion automatically?

I considered an automatic promotion path but decided against it I want to actually review the data myself first.

What's your model churn rate like? I was worried about customer experience by same day maybe same work getting a totally different model response (also caching is worse)

I'm confused, what do they mean when they say they reduced prices?

DeepSeek v4 flash is $0.10 / $0.25 as opposed to this v4.1 bump which is $0.30 / $1.20

You're looking at third party providers.

V4 Flash prices served by DeepSeek themselves:

  launch pricing: $0.0028 / $0.14 / $0.28 
  after Aug 16th: $0.007  / $0.22 / $0.66 during off-peak.
  after Sep 10th: $0.003  / $0.15 / $0.60 during off-peak.

Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, rate is doubled.

https://api-docs.deepseek.com/quick_start/pricing (archive.org for old)

This is supposed to be a replacement for the v4 pro model.

So it is price increment in the end, if new pro model comes with the new pro price.

Don't know where you got those numbers from. Check old prices here: https://web.archive.org/web/20260907112235/https://api-docs.....

Input tokens are around half the cost, output only slightly cheaper.

Right now in OpenRouter it's 3x/3.75x more expensive than V4 flash but the cache read is around 4x cheaper.

I haven’t reverse-engineered the GrokBot comms layer but it’s pretty similar in experience

not impossible, pypush did it 3 years ago

Yes, it is awfully inconsistent today. They run some tests (accuracy table buried on model page) but they are sparse and only capture a single moment in time. I would love to see OpenRouter take this more seriously.