GLM-5.2 Fast is now live on Command Code! The high-throughput build of GLM-5.2, same frontier coding, now at 120–250 tokens/sec for snappier long-horizon runs. 1M context. Tool use. Reasoning. Available in the $1 Go plan with $10 usage credits and above!! Try it out now with /model.

@CommandCodeAI So basically a paid version of what was free last year.

@CommandCodeAI Two prompts and the quota was used up 😂

@CommandCodeAI Alguma previsão do 5.2 short?

@CommandCodeAI price??????

@CommandCodeAI I want to try the command code paid plans, but I don't know what's the problem with your signup. I created an account using my email ID. I have got the verification OTP. Everything is done, but it is not logged in. I have tried with two to three Gmail IDs, but I am unable to do

@CommandCodeAI GLM‑5.2 Fast at 250 tokens/sec with 1M context? That's insane through put for long‑horizon coding Speed + power = dev dream!

@CommandCodeAI It's really unfortunate that you guys are keeping 5 hour and weekly limits, the only reason I came to your platform is it has no 5 hour limits.

@CommandCodeAI But still no vision?

@CommandCodeAI GLM-5.2 Fast is live 120–250 tokens/sec, 1M context, tool use + reasoning. Snappy long runs from $1.

@CommandCodeAI Pricier than non-fast?

@CommandCodeAI Rate limit 👎👎👎👎👎👎one prompt you can't use command code. We don't need rate limit

@CommandCodeAI was waiting for it, although token usage is so unpredictable in commandcode