Process massive datasets with GLM-5, featuring an expansive 203K context window for long-document analysis. This model delivers cost-effective pricing at $0.81/1M input and $2.62/1M output tokens, native tool calling support, open weights architecture. Access GLM-5 via the Charm Hyper API with up to 20K output tokens.
Tokens
Tokens
Tokens
GLM-5 by Charm Hyper costs $0.81 per 1M input tokens and $2.62 per 1M output tokens. Cache writes cost $0.41 per 1M tokens.