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

121–130 of 433 posts

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

#121

Post by agentdev001 »

mft_ wrote: post #78
bel8 wrote: post #44

Earlier quoted context omitted.

It's easy to add using plugins. What do you miss? I ask because I do some heavy work with pi + GLM 5.2 (using opencode Go subscription) and my workflow is plan -> implement.

> It's easy to add using plugins. Sure, but you have to add almost everything, no? It deliberately only comes with read, write, edit, and bash. My point wasn't that you can't add stuff, but that I'd just rather use an harness that's a bit more full featured from the start. (Pi is a bit like old 3D printing where fettling the printer to work is a central part of the hobby. I'd rather just buy a Prusa.)

I'd like to understand what features you're referring to that are missing from base-install Pi CLI.

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

#122

Post by diurnalist »

hobofan wrote: post #75
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.

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

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.

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

#123

Post by anonu »

This is all heading in the right direction. Much of AI coding feels magical. But when the costs begin to accrue we start asking questions. We dig into it and try to understand what's going on. I can't help but feel Anthropic is "token maxing" from its side: it controls the levers and with every version upgrade it can build in its own token growth almost unbeknownst to the user. This actually harms it on the long run because it necessitates a cheaper option.

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

#124

Post by athrowaway3z »

claw-el wrote: post #88
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.

I bailed on Anthropic the moment they started blocking alternative harnesses like pi on their subscription plans.

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

#125

Post by docheinestages »

arcanemachiner wrote: post #28
docheinestages wrote: post #20

I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, regardless of the model. What is the best harness and on-device model combination right now?

You can't afford the best model. What are your specs and what models + quants have you tried? Qwen 3.6 35B A3B and Qwen 3.6 27B can both do reliable tool calls on Pi at Q4_K_M using llama.cpp

I'm on a 48 GB M5 Macbook Pro. I use 4-bit quants with a context window of 16-32k. I tried Qwen 3.6 27B, but I can only get around 10 tokens per second, but it's painfully slow, and it often fails during `write_file` tool calls, even with Qwen Code.

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

#126

Post by reinitctxoffset »

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…

Subagents with a fat tailed latency distribution completely masks the trough filling that puts the most downwards pressure on per-token COGS.

This is why the subscription plans are forced through the harness (the "OpenClaw Wars"): it creates a false equivalence in the minds of many customers between API tokens (latency sensitive, easy to measure) and Claude Code tokens (remnant backfill to stay to the right of the roofline, marginal cost often zero).

Selling sausage as sirloin is a great business if people go for it. And there's nothing inherently wrong with spot pricing, as long as you're honest about it...

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

#127

Post by kadoban »

beezlewax wrote: post #115
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…

Spawning a bunch of agents seems to happen randomly. I almost never want this.

I think there's some setting to restrict the number of them, or maybe turn them off. Doesn't happen for me ~ever and it's not my $$ (work) so I haven't really looked at it much.

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

#128

Post by alex7o »

venusenvy47 wrote: post #89
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?

yep I pass it to the CLI, I also pass --model

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

#129

Post by yearolinuxdsktp »

docheinestages wrote: post #20

I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, regardless of the model. What is the best harness and on-device model combination right now?

Pi.dev requires some plugins to work well. Using Qwen3.6-27B/35B locally at Q8, I was quite frustrated with failed tool calls and tried many things.

Ultimately this combo worked:

1. https://pi.dev/packages/pi-tool-guard —- corrects key name synonyms and common structure errors, so tool calls succeed automatically (e.g if the model hallucinates old_str instead of oldText). It also wraps top level oldText/newText in an edits array if the tool didn’t do it.

2. https://pi.dev/packages/@aboutlo/pi-smart-edit - white-space-tolerant edits, as Qwen would sometimes add a fifth space to a four space indent

Hashline edit tools didn’t work well for me at all, they confused the model and it still failed to edit correctly. Also line removals would invalidate the rest of the file requiring re-reads. I tried pi-hashline-edit-pro, though I see it now keeps a database of hashes to help keep them stable across edits. Regardless Qwen kept thinking that the hashline prefixes were part of the source.

Post reply on HN