GLM-4.5

GLM-4.5 is a conversational large language model developed by Z AI (the developer behind the GLM series). It sits in the GLM-4 generation of the family as a general-purpose chat model, intended for assistant-style interaction, instruction following, and text generation tasks rather than for a single narrow specialty. On this page it is listed alongside the providers that serve it through inference APIs, so the same model name may be available from more than one endpoint. Our database records GLM-4.5 as a chat model from Z AI. We do not currently track a confirmed context window length, modality list, or per-provider throughput figures for this entry — the latency and tokens-per-second values we hold are unpopulated, so any speed comparison should be taken from the provider's own documentation or from independent measurement rather than from this listing. Where a specification matters for your deployment, verify it against the serving provider, since providers can differ in the maximum context they expose, the quantization they run, and the API surface they offer. In practice, models in this position are used for the broad middle of LLM workloads: chat assistants, drafting and rewriting, summarization, question answering over supplied text, and code assistance. GLM-4.5's practical appeal for many teams is provider choice — when a model is served by multiple inference vendors, buyers can compare per-token cost, throughput, and region availability for the same weights instead of being tied to a single vendor's terms. Use the pricing table on this page to see which providers currently serve GLM-4.5 and how their rates compare.