GLM-5

A bit off-topic but I’m on the legacy Lite plan (now discontinued), and it’s more than enough for hobby projects. The main draw is the generous request-based quota (18k requests/month) rather than a token-based one. This means a 100k token request counts the same as a 100-token one. I’ve made about 8000 requests in the last two weeks, averaging around 80k tokens per request. It feels like they’re subsidizing this just to gather data on agentic workflows. On the downside, the speed is mediocre (15–30 tg/s for GLM-5), and I’ve seen the model glitch or produce broken output about 10 times out of those 8k requests.

I'm 50% convinced that the main lift in GLM-5 over GLM-4.7 was that it was much more willing to use tokens. I had the hardest time getting 4.7 to read enough source code to actually know what it was doing, but once I convinced it to read, it was pretty capable. Being thrifty can be good! But it also can mean your system is not reflecting sufficiently, is not considering enough factors, isn't reading enough source code. We are still firmly in "who really knows" territory. I have mixed feelings about token spendiness vs thrift, is all.

Interesting. Chatting GLM-5(reasoning)(preview) answers just fine. Even after restricting web search and giving answer based on its own knowledge. Probably the results were different in China? (GLM-4.7 failed to know anything without web search)