Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

systima.ai

Post reply on HN
Print view View original

61–70 of 433 posts

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#61

Post by jchook »

FuckButtons wrote: post #58
paxys wrote: post #54

Earlier quoted context omitted.

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.

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

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…

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#62

Post by AndyNemmity »

alex7o wrote: post #13

I am forced to use cloude code at work but a good solution is to just use --system-prompt "" and be done with it. I wish they allowed for other harnesses.

Yep, have been using this for a long time now. No idea why everyone doesn’t.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#63

Post by qpricjalcbeu »

mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

And in my experience the sub agent performance is usually worse than just a single agent.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#64

Post by lanthissa »

korrectional wrote: post #26

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.

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.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#65

Post by SyneRyder »

llm_nerd wrote: post #46
andai wrote: post #29

With Fable being per token instead of on the subs (unless they changed it again?), I decided to test Claude code on OpenRouter where I had some credits, with Opus 4.8 and Fable 5. I asked both a trivial question (summarize last commit). Opus cost 50 cents, Fable about $1. That checks out because Fable's twice as much in the API (though I think its emphasis on correctness makes the difference larger for bigger tasks).…

Fable's subscription inclusion theoretically ends EOD today. Anthropic put a wishy-washy "if we have capacity we'll continue it" thing, and given how competitive GPT 5.6 Sol is, and it is included in OpenAI's subscription, I fully expect Anthropic to extend Fable or they will have a serious exodus on their hands. Competition is good.

Anthropic have extended Fable access again to July 19. The notice should pop up in your Claude Code now when you start a new session (also announced on the ClaudeDevs X account first).

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#66

Post by tmalsburg2 »

tontinton wrote: post #37

Mine sends even less - https://maki.sh

Nice!

> When context gets too long, maki compacts history automatically: strips images, thinking blocks, and summarizes older turns.

Don’t the summaries of older turns effectively invalidate the context cache, such that you consume less tokens but more expensive tokens?

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#67

Post by retired »

mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

Did it deploy five AWS m8g.12xlarge instances?

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#69

Post by VulgarExigency »

paxys wrote: post #54
korrectional wrote: post #26

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.

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.

Enterprise users are not paying a fixed fee, though

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#70

Post by dymk »

prymitive wrote: post #18
jakozaur wrote: post #5

This isn’t limited to large system prompts. Coding-agent harnesses are also becoming more aggressive about using tools, even for trivial requests. In our tests, prompts such as “Hey” or “commit” sometimes triggered 30+ tool calls: https://quesma.com/blog/the-true-cost-of-saying-hi-to-an-ai-... Tokenflation seems very real: the number of tokens consumed by simple tasks keeps increasing.

I often find myself annoyed when Opus fixes a typo in a comment and decides to run tests, lints and whenever else it can find to run. Often it will start by stashing current changes just to preemptively check if all tests were passing before. And I can blame myself a bit because my rules do say: verify all changes with tests. But as there is that I in AI that is hyped which you’d think means it knows not to put tomat…

Add "... unless the changes are trivial, docs-only, or typo fixes" to the "always verify with tests" instruction and see how that does
Post reply on HN