Claude Token Counter, now with model comparisons

Re:Claude Token Counter, now with model comparisons by aliljet on Monday April 20, 2026 @01:34AM (#47830716)

This is the rugpull that is starting to push me to reconsider my use of Claude subscriptions. The "free ride" part of this being funded as a loss leader is coming to a close. While we break away from Claude, my hope is that I can continue to send simple problems to very smart local llms (qwen 3.6, I see you) and reserve Claude for purely extreme problems appropriate for it's extreme price.

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by KronisLV on Monday April 20, 2026 @02:29AM (#47831016)

> This is the rugpull that is starting to push me to reconsider my use of Claude subscriptions.

I'm still with them cause the model is good, but yes, I'm noticing my limits burning up somewhat faster on the 100 USD tier, I bet the 20 USD tier is even more useless.

I wouldn't call it a rugpull, since it seems like there might be good technical reasons for the change, but at the same time we won't know for sure if they won't COMMUNICATE that to us. I feel like what's missing is a technical blog post that tells uz more about the change and the tokenizer, although I fear that this won't be done due to wanting to keep "trade secrets" or whatever (the unfortunate consequence of which is making the community feel like they're being rugpulled).

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by rimliu on Monday April 20, 2026 @03:36AM (#47831359)

20 USD tier was useless from the start. You'd get to the limit in 30 minutes. Codex with 20 USD on the other hand...

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by adezxc on Monday April 20, 2026 @08:31AM (#47833337)

Give Codex a month or two and it'll just do the same thing, though now with a million more users because Claude Code wasn't good enough.

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by arw0n on Tuesday April 21, 2026 @07:20AM (#47847266)

I'm on the 20 USD tier, and it works quite well for me. Basically I send one very carefully crafted task to the LLM per 4h limit, do a couple of minor questions, and the rest of the time I'm thinking/exploring/coding. I am producing around a tenth of the code of my colleagues, but around the same number of features.

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by londons_explore on Monday April 20, 2026 @01:43AM (#47830766)

I think an LLM that is a decent chunk smarter/better than other LLM's ought to be able to charge a premium perhaps 10x or 100x it's competitors.

See for example the price difference between taking a taxi and taking the bus, or between hiring a real lawyer Vs your friend at the bar who will give his uninformed opinion for a beer.

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by teaearlgraycold on Monday April 20, 2026 @03:34AM (#47831353)

For now you can run /model claude-opus-4-6

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by DeathArrow on Monday April 20, 2026 @01:43AM (#47830767)

Quality of answers from quantized models is noticeable worse than using the full model.

You'll be better using Qwen 3.6 Plus through Alibaba coding plan.

[ Parent | on HN ]

Re:Claude Token Counter, now with model comparisons by SoMomentary on Monday April 20, 2026 @07:49AM (#47832956)

> Quality of answers from quantized models is noticeable worse than using the full model.

This is the very reason I've heard I shouldn't use Alibaba!

[ Parent | on HN ]