Hm. I must be holding it wrong. I hit $20 easily in 5 hours with deepseek in opencode.

Same here - curious which deepseek model and what op was doing.

I suspect it might be a question of conversational loop vs agentic dev - the former uses much less tokens than letting an autonomous agent churn away on your codebase.

Do a through audit of every single token you're sending and receiving. Some harnesses include things you didn't expect.