Hacker News: aray07

New comment by aray07 in "Claude Fable 5"

aray07 — Tue, 09 Jun 2026 17:22:14 +0000

i have never seen this before - where you offer something and then take that away

Why images use 3x more tokens in Claude Opus 4.7

aray07 — Tue, 21 Apr 2026 14:45:22 +0000

Article URL: https://www.claudecodecamp.com/p/images-cost-3x-more-tokens-in-claude-opus-4-7

Comments URL: https://news.ycombinator.com/item?id=47849545

Points: 3

# Comments: 0

Images cost 3x more in Opus 4.7

aray07 — Mon, 20 Apr 2026 13:21:54 +0000

Article URL: https://www.claudecodecamp.com/p/images-cost-3x-more-tokens-in-claude-opus-4-7

Comments URL: https://news.ycombinator.com/item?id=47833947

Points: 2

# Comments: 0

New comment by aray07 in "Opus 4.7 to 4.6 Inflation is ~45%"

aray07 — Sat, 18 Apr 2026 17:51:55 +0000

Came to a similar conclusion after running a bunch of tests on the new tokenizer

It was on the higher end of Anthropics range - closer to 30-40% more tokens

https://www.claudecodecamp.com/p/i-measured-claude-4-7-s-new...

New comment by aray07 in "Claude Opus 4.7 costs 20–30% more per session"

aray07 — Fri, 17 Apr 2026 17:17:38 +0000

yeah thats the part that is unclear to me as well - if our usage capacity is now going to run out faster.

New comment by aray07 in "Measuring Claude 4.7's tokenizer costs"

aray07 — Fri, 17 Apr 2026 17:16:11 +0000

im running some experiments on this but based on what i have seen on my own personal data - I dont think this is true

"given that Opus 4.7 on Low thinking is strictly better than Opus 4.6 on Medium, etc., etc.”

Opus 4.7 in general is more expensive for similar usage. Now we can argue that is provides better performance all else being equal but I haven’t been able to see that

New comment by aray07 in "Claude Opus 4.7 costs 20–30% more per session"

aray07 — Fri, 17 Apr 2026 17:05:08 +0000

effort level is separate from tokenization. Tokenization impacts you the same regardless.

I find 5 thinking levels to be super confusing - I dont really get why they went from 3 -> 5

New comment by aray07 in "Claude Opus 4.7 costs 20–30% more per session"

aray07 — Fri, 17 Apr 2026 17:04:02 +0000

i think the new qwen models are supposed to be good based on some the articles that i read

New comment by aray07 in "Claude Opus 4.7 costs 20–30% more per session"

aray07 — Fri, 17 Apr 2026 16:51:41 +0000

anthropic’s pricing is all based on token usage

https://platform.claude.com/docs/en/about-claude/pricing

So if you are generating more tokens, you are eating up your usage faster

New comment by aray07 in "Measuring Claude 4.7's tokenizer costs"

aray07 — Fri, 17 Apr 2026 16:50:39 +0000

are you okay with paying more for your services without any perceived improvement in the service itself?

New comment by aray07 in "Claude Opus 4.7 costs 20–30% more per session"

aray07 — Fri, 17 Apr 2026 16:49:45 +0000

yeah thats is my biggest issue - im okay with paying 20-30% more but what is the ROI? i dont see an equivalent improvement in performance. Anthropic hasnt published any data around what these improvements are - just some vague “better instruction following"