Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- This is half the story; you should show performance per dollar. I doubt your 2x approach would fare well against the priority if you consider the costs.by behnamoh
- The article mentions that the priority tier costs 2x normal, so the costs of running normal twice should be fine.
- If you want a controllable and predictable system, host it yourself. APIs will always have outages, delays and breaking changes every so often. That's the price you pay for not doing it properly and outsourcing your job.by moffkalast
- > host it yourself. APIs will always have outages, delays and breaking changes every so often.
Since you've solved all of these problems, including hardware, etc, you should expand this to a business! Many people would be very interested in an "Infinite 9's" (potential business name there) uptime service!
by nomel - for a tier thats twice the cost i would expect >2x the speed. somewhere 5-10x
e.g. 1.40m would become 0.30s.
do people really pay for these priority plans?
by ramon156 - I love this. Simple. Useful. To the point. If AI was used, I can't tell because it is clearly representing the author's beliefs.by eigenblake
- agreed, reads like a breath of fresh air, no fluff
- Why not send it thrice?by crisnoble
- It turns out that best of 2 random draws outperforms best of 1, best of 3, and best of all in many load balancing scenarios: https://brooker.co.za/blog/2012/01/17/two-random.html
It's a bit unintuitive, but they key idea is roughly 'If you're working on stale load data (as always), best of 2 strikes the right balance between distributing load evenly and giving more work to less loaded hosts'. If you do 'best of k', you end up with herd behavior, overloading one host. 'best of 1' sends too much traffic to slow hosts.
by ball_of_lint - Nice turn around, does anyone has a benchmark regarding other types of requests (priority vs send twice) other than voice/call? Or the tests already test that?by dvaplima
- Is there a way to do this automatically when using claude/codex?by sharts
- Sending two identical parallel requests is the classic approach. But, logically speaking, it should also double the cost.
I would send a second request if the first request fails to return the first token within, say, 1 second. Then there's a chance the first request is stalling, which is an infrequent event.
I wonder if higher-availability tiers of LLM providers do a similar thing internally.
by nine_k - Token caching might help here, but if it returns the same result, faster, for the same price as priority, seems good
- This sounds like a job for Fast Fallback instead: https://en.wikipedia.org/wiki/Happy_Eyeballsby Groxx
- You don't have to send every single request twice, just the ones that are haven't returned in time. Wait until some threshold, such as your p95 latency, and send your backup request after that. Return whichever request comes back first, and it should cut your tail latency without doubling your cost, since it only duplicates the small % of requests at the tail.
Google calls this a 'hedged request': https://cacm.acm.org/research/the-tail-at-scale/
by ak_t