I buy DeepSeek and MiMo directly from them, on the assumption they're better at it, have a vested interest in me having a good experience and they'll get caching and other stuff right. They're also cheap enough that it's unlikely you'll find a much better deal on those models.

I'm likely to also add a small Kimi Code subscription, as the model looks very promising and I don't see any reason to support proprietary US models from companies I don't really trust overopen Chinese models. I've opted not to get a z.AI subscription, though, as the price/performance ends up not being great, because GLM chews a lot more on the problem so its actual price per task is roughly the same as the big guys. The same can't be said of DeepSeek. It's notably cheaper per task, especially when comparing API rates to Anthropic or OpenAI.

I use GLM 5.2 through open router, and it's much much less expensive than Anthropic/GPT5.5. I do app development with it and I spend maybe $0.20-$0.50 per task that I work on expanding the app where Claude sonnet will come out to $1-2 for the same work, and Claude Opus $5-10