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

81–90 of 433 posts

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

#81

Post by micw »

a_c wrote: post #73
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…

Every subagent send the same ~30k system prompts. If you are using fable/opus, that's easily 30% of a 5-hour window for 7 subagent, before doing any work

I recently did a few tests. And always the same prompt has been cached properly.

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

#82

Post by echelon »

token_roast wrote: post #68

Why don't people fix their costs (rent a gpu) and just write their own harness (about 200 lines of code). Supposed to be hacker news and half the posts are like "this harness steals this" like it cant be avoided. These API costs are mad.

GLM isn't good enough yet.

It pays to be marginally ahead of people stuck on open models.

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

#85

Post by megous »

a_c wrote: post #73
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…

Every subagent send the same ~30k system prompts. If you are using fable/opus, that's easily 30% of a 5-hour window for 7 subagent, before doing any work

If it's always the same prompt, can't they have it pre-cached globally for all?

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

#87

Post by bpodgursky »

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.

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

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

#88

Post by claw-el »

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.

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.

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

#89

Post by venusenvy47 »

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.

Do you start Claude with this option? Or do you send this with every prompt?

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

#90

Post by wongarsu »

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…

Sub agents each have to read part of your code base again to get enough context for the task. And if they take too long, your orchestrator's context is no longer in cache so you pay full price for that again once the subagents finish

If you do it sequentially you only read those files approximately once, and everything hits the same prefix cache

Post reply on HN