My opinion is that claude code uses more tokens simply because Anthropic makes more money that way and forces people into their subscriptions. This is supported by the fact that they won't let you use your sub on a different coding agent. I use pi btw.

▲ claw-el an hour ago | parent | next [-]

Once I realized that Anthropic is a token merchant, I start to understand Anthropic’s decision more. They are always finding reasons for you to use more tokens through them unless the users revolt or demand some guardrails.

	▲	nijave a minute ago \| parent \| next [-]
		I've done a couple side by sides on web chat with the same prompt on Opus 4.6, 4.7, and 4.8 and the output gets longer/more verbose on version increment. The enerr variants are definitely much wordier. On the other hand, the newer variants also tend to benchmark higher so it's not quite a clean argument of "hey the new version eats more tokens"
	▲	athrowaway3z 32 minutes ago \| parent \| prev \| next [-]
		I bailed on Anthropic the moment they started blocking alternative harnesses like pi on their subscription plans.
	▲	lkbm 9 minutes ago \| parent \| prev \| next [-]
		Seems unlikely they'd be this dumb. The way to get us to use more tokens is to make those tokens more useful, not less. Anthropic is full of people (including higher-ups) who know this.
	▲	cyanydeez a minute ago \| parent \| prev \| next [-]
		now reealize that LLMs are trained to produce tokens and like the halting problem, cant be trained not to produce tokens and youll realiE the AI labs are the perfect essential capitalist and like cancer, will keep growing useless tokens until it kills its host. no amount of alignment will stop aomeone drom just shutting up.
	▲	stefan_ an hour ago \| parent \| prev [-]
		But they gave us double the tokens! Then a limited time more usage! Then even more tokens "off peak" times! Then some new model released but apparently it inherently used 1.69x tokens! Then Fable is here but "it uses much more usage". But only until ~~the US banned it~~ ~~7th July~~ ~~19th July~~ who even knows. At this point I think Dario is just in his wellness retreat adjusting a revenue/profit dial.

▲ toddmorey 2 hours ago | parent | prev | next [-]

I thought I read somewhere that according to filings for going public, subscription revenue is tiny… like 5%.

Edit: consumer Claude subs are the 5%. I’d bet most all of CC subs lump in under enterprise.

  - API & Enterprise: 75% to 85% of total revenue.
  - Business Subscriptions: Roughly 10% to 15%.
  - Individual Subscriptions: About 5%.

	▲	Quot 2 hours ago \| parent [-]
		The vast majority of my company's enterprise plan use is through Claude Code even though we have access to the API and could be using OpenCode instead. I don't fully agree with the premise that they intentionally increase system prompts, but the enterprise plan usage is going to make that a huge income for Anthropic.

▲ paxys 2 hours ago | parent | prev | next [-]

You're making the opposite argument. Anthropic is incentivized to use less tokens in Claude Code because people are paying a fixed monthly fee for subscriptions.

▲

FuckButtons 2 hours ago | parent | next [-]

Nope, that’s not true, because they want you to pay for the higher subscription bracket.

▲

jchook 2 hours ago | parent | next [-]

Can confirm — they got me paying $100/mo this way.

Also I think it’s well known that OpenAI is the much less expensive option (in tokens and $$). For the same $20 you get a lot more mileage.

Curious if folks have strong opinions about the overall UX of OpenCode vs CC…

	▲	erikus an hour ago \| parent [-]
		For me as well, at least this month to use more of Fable. We'll see if they extend Fable access because of people like me.

▲

tjoff an hour ago | parent | prev | next [-]

Well since what you get for your subscription is unknown it would be trivial to get that result without burning tokens.

Especially since compute is such a scarce resource.

▲

bpodgursky an hour ago | parent | prev [-]

If they wanted to play games with sub tiers they would just change the rate limits rather than wasting inference.

▲

VulgarExigency an hour ago | parent | prev [-]

Enterprise users are not paying a fixed fee, though

	▲	whazor an hour ago \| parent [-]
		Yeah, I strongly recommend against Claude Enterprise, it is ridiculously expensive and hard to control costs.

▲ hobofan an hour ago | parent | prev | next [-]

> I use pi btw

Not sure if intentionally meant as a reference, but it gives "I use Arch btw" vibes.

	▲	diurnalist 41 minutes ago \| parent [-]
		Pi is one of the ways out of this problem (OpenCode another) so I took it as an intentional reference as it is highly relevant. I also use Pi as my daily driver and I think it's a wise choice to figure out how to decouple yourself from lab-specific harnesses that you have little control or observability over.

▲ lanthissa 2 hours ago | parent | prev | next [-]

the amount of system prompt wastage going on in orgs is insane. we identified 400k in annual burn for zero value in just one section of our large company.

and the interesting thing about system prompt wastage is its a cost that scales non linearly with subagent use.

▲ hvb2 2 hours ago | parent | prev [-]

> This is supported by the fact that they won't let you use your sub on a different coding agent

I mean, that's a very weak argument? Isn't a much more plausible explanation that with your tooling you'll have more of a lock-in than with just your model?

	▲	notnullorvoid 10 minutes ago \| parent [-]
		Neither is mutually exclusive. They get lock-in, and through that lock-in are more effectively able to inflate token usage.