The reasoning built into the models matter so much too. I recently swapped my Qwen3.6 27B to ThinkingLabs’ fine tune and it does what it publishes. I cut my token usage in half, which is a big deal since I only get ~20 TPS for token generation.
Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
91–100 of 433 posts
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#92Earlier 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.
Enterprise users are not paying a fixed fee, though
Yeah, I strongly recommend against Claude Enterprise, it is ridiculously expensive and hard to control costs.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#93Earlier quoted context omitted.
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?
I'm pretty sure the system instructions are a function of your environment and not the same universally. That said, there should be a finite number of branches so still cacheable.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#94Earlier 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.
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.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#95Is it not a conflict of interest for a model provider to supply the harness? They are not motivated to minimize your costs.
They sort of are, in that they want subscription users to have clients that behave well with the KV cache etc.
If you don't use a subscription, and pay per token instead, you can easily move to another harness.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#96Early on in experimenting with local models, I found that hooking them up to Claude Code worked very well, but it was also really slow. I used mitmproxy (setup assisted by Claude, natch) to capture Claude Code's entire initial system prompt and the whole thing was (I just double-checked) 162k of JSON. This led me to start experimenting with Pi, OpenCode, and Hermes...
This is interesting, because if I start a fresh session of Claude Code right now and run /context, I see the following: Opus 4.8 (1M context) claude-opus-4-8[1m] 23k/1m tokens (2%) Estimated usage by category System prompt: 3.9k tokens (0.4%) System tools: 13.9k tokens (1.4%) Custom agents: 235 tokens (0.0%) Memory files: 28 tokens (0.0%) Skills: 4.9k tokens (0.5%) Messages: 8 tokens (0.0%) Compact buffer: 3k tokens…
Apologies, you're right - I used imprecise terminology. The entire initial JSON structure that was sent from Claude Claude to the LLM at the start of a session was 162k. This included the system prompt together with a list of tools (some with very extensive explanations), MCP server details, etc.
I was simply supporting the article's data - their reported 33k tokens is probably roughly 150-165k.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#97Earlier quoted context omitted.
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…
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.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#98Recently switched to Codex after 6m in Claude. Codex seems more open, it’s easier to follow what the model is doing and the approvals have a better UX. Overall, it just feels more transparent. Cost of switching was close to 0. I don’t like that Claude became more opaque around February, including the system prompts. 33k feels way too much.
What settings have you tried since it "became more opaque"? They've got a lot more settings now.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#99UPDATE: After reading PUSH_AX's valid comment: ``` This is like saying contractor (A) asked for $33,000 to undertake the work and contractor (B) asked for $7,000 Are we measuring and caring about the right thing? ``` We will update the post to include: 1) A more in-depth task. 2) Qualitative results comparison. 3) As soon as possible, a reproduction of the inputs and outputs.
Thanks, I'm looking forward to this!
I wonder if a lot of the 33k is context, like from recent conversations.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#100What 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…
> 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.
Probably because the general purpose subagents inherit the parent model.
I tell Claude explicitly to use Explore subagents, which use Haiku only, now.