GLM 4.5 is a great budget option for me. After cancelling Claude sub ($20 USD one), I've been trying Gemini 2.5 Pro through Gemini CLI, and it was okay for landing pages and UI. However, I switched to GLM through Claude Code using their cheapest subscription and it's been pretty good so far. It feels more creative than Gemini when it comes to UI, not Claude Sonnet level (can't compare with Opus), but it's 90% there. It also follows instructions better than Gemini, and makes fewer or no syntax errors. Gemini through Gemini CLI would somewhat often completely mess up Astro files, or be a bit lazy. No such problems on AI Studio though.
A few days I got their quarterly promo plan ($9 USD), so I'm excited to try 4.6.
Just register a subscription [1] with z.ai (company behind the GLM models), get an API key [2], and then put something like this in your ~/.zshrc or ~/.bashrc, etc:
alias zcc='ANTHROPIC_BASE_URL="https://api.z.ai/api/anthropic" ANTHROPIC_AUTH_TOKEN="your z.ai api key" claude --model GLM-4.6'
Do you mean people bought committed plans the moment the new Anthropic models dropped yesterday? TBH I think it’s wise with LLM coding agents to try everything, and avoid sticking to one solution until the space matures.
It would be great if people that are using GLM-4.6 within Claude Code could chime in with their experience in using it. I'm a MAX subscriber and having extra cheap tokens would be very helpful.
The most used opensource agentic coding model, Qwen 3 Coder, is completely missing from all the comparisons. That's what everyone who uses these models wants to compare it with. A missed opportunity.
A few days I got their quarterly promo plan ($9 USD), so I'm excited to try 4.6.