I haven't tried $20 claude code recently, but I've used OpenCode Zen primarily so I can play with opensource/chinese models which are very inexpensive. I'd spend $0.50-$1.00 on a single claude opus 4.6 plan mode run, then have a chinese model execute the plan for like $0.10-$0.15 total. I'd keep context short, constantly start new threads, and get laser focused markdown plans and knowledgebase to be token efficient.

If I just let opencode zen run claude opus to plan and execute, I'd spend $20 in like 5 minutes lol

Which chinese models do you use and do you use any for specific tasks?

Whenever a new one comes out, there's a good chance they're free for a week on Zen, so I try out any free ones. For example, MiniMax M2.5 and Qwen 3.6+ are free right now.

Personally, I've had a lot of good results in my little personal projects with Kimi K2.5, GLM 5 and 5.1, and MiniMax M2.5.

kimi k2.5 works quite well and is super fast. Much faster than opus but not quite at the same quality level.

I mostly use Opus via Copilot with opencode, and I'll tell you, in the past few days, I've had long sessions (almost the whole day) without hitting rate limits. That's very different from Claude Code, which used to rate-limit me before even halfway through the day.

Just cancelled my Claude plan, so that I can switch over when it expires in a week. The usage limits somehow just make me less productive with it.