Claude March 2026 usage promotion(support.claude.com) |
Claude March 2026 usage promotion(support.claude.com) |
There is no way 5-11 AM PT is peak traffic
* This is the regular price window, the rest is the promo usage.
Thanks for clearing that up. It'll help me schedule stuff in the future.
If you are only using a session a day, you're wasting a session. :)
Also, my (extremely naive) understanding is that at the cutting edge, hardware is diverging for training vs inference. That might not be true for Anthropic though.
Most of these Behind the Meter generation projects will be Gas Generation. Guess what happens during a cold snap like the one we experienced in the Northeast US a few weeks ago? Natural gas prices jumped 10X in the daily market. You say that they are hedged? Hedges do not matter during Operational Flow Order(OFO)/Force Majeur/Curtailment pipeline events and they are exposed to the daily market. (I do this for a living)
What I wish Anthropic would do is be a lot more explicit about what windows apply when. Surely they have the data to say "you get X usage from hours A to B, Y usage from B to C"
Regular price window around the world: https://www.worldtimebuddy.com/?qm=1&lid=5368361,5128581,316...
From my understanding: Peak time (non-promo): UTC 12:00–18:00 / KST (UTC+9): 21:00–03:00 Off-peak time (promo): UTC 18:00–12:00 / KST (UTC+9): 03:00–21:00
I guess I’ll need to do more coding during the daytime.
So much for that plan.
"One thing I really suspect we'll see a lot more of is much more generous rate limits at 'off peak' times - likely to be early morning UTC - as there is no doubt a lot of "idle" compute sitting there"
I strongly suspect this will end up in the opposite happening - where peak tokens are far more "expensive" (whether that be thru usage limits of API costs) than off-peak.
PS: Anthropic have managed to improve reliability but are absolutely shredding opus tok/s at peak times. It absolutely crawls on the web (maybe 2-3 tok/s?) and I believe that on non-max plans it's also incredibly slow on claude code.
This only happens once/if competition eases up. Until then, it’s a race to the bottom
Perhaps an opportunity for them to improve workload scheduling orchestration, like submitting a job to a distributed computing cluster queue, to smooth demand and maximize utilization.
So they could “double” your usage by keeping it the same and then simply halving peak usage.
So us European folks get promotional rates during the morning and evening.
EDIT: Actually, because the promo ends at the end of March, it'll all be within DST shenanigans. So peak times are 12:00–18:00 London, 13:00–19:00 Berlin.
If they are doing it “right” I think any off peak usage should count 50% toward your weekly limits.
Edit: it does look like they are doing it the "right" way.
> No. The additional usage you get during off-peak hours doesn’t count toward any weekly usage limits on your plan.
I'm not sure how to square that with the quote you gave.
> No. The additional usage you get during off-peak hours doesn’t count toward any weekly usage limits on your plan.
codex is still in minority use but has taken many customers from them over a short period.
Peak hours (normal usage): 8 AM – 2 PM ET → 12 AM (midnight) – 6 AM AEDT (next day)
Off-peak hours (2x usage): All other times → 6 AM – 11:59 PM AEDT
We all know these services see huge load spikes and sometimes service degradation when America wakes up, and I bet they'd appreciate it if as many "chug-and-plug" agent workflows moved to overnight hours as possible.
I think these token doubles are there to kick you into a abundance mindset (for want of a better term) so going back feels painful. Stop counting tokens, focus on your project and the cost of your own time.
When you say nearly unlimited token, do you mean the 100 or 200$ subscription?
Plus we are technologists, we want to try out different stuff and compare.
I mainly use it for side projects and doing research for writing stuff on my blog.
I use Opus 4.6 with claude code 1M context and consistently use up 150-200$ worth of token per day. I wonder how do you manage to do anything with a 10$/mo program.
https://platform.claude.com/docs/en/about-claude/models/over...
Text includes:
Invoke each review/audit skill in sequence. Each skill runs its own comprehensive checks and returns findings. Capture the findings from each and incorporate them into the final report.
IMPORTANT: Invoke each skill using the Skill tool. Each skill is independently runnable and will produce its own detailed output. Summarize findings per skill into the unified report format.
4. Architecture Health
Invoke: Skill(architecture-review)
Covers: module boundaries, cross-module communication, dependency direction, infrastructure layer rules, hexagonal architecture compliance.
5. Security Health
Invoke: Skill(security-review)
Covers: hardcoded secrets, SQL injection, authorization, HTTPS, CORS, input validation, authentication patterns.
But them even admitting that was possible is a little bit to close to being able to be held accountable...
But increasingly I'm using Claude for basically all real coding. I ask Gemini and Codex questions, but I'm honestly in awe at Opus' ridiculous capabilities.
Before that I would totally agree with you, it felt really endless