GLM 5.2

GLM 5.2 is a Fireworks model available in Agent Serve. GLM 5.2 is a Fireworks model tracked in Agent Serve. It supports a 1.05M token context window. Pricing starts at $1.4/1M input tokens and $4.4/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.

GLM 5.2 starts at $1.4/1M input tokens, $0.14/1M cached input tokens, and $4.4/1M output tokens.

GLM 5.2 supports a context window of 1.05M tokens in Agent Serve. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

GLM 5.2 supports the following capabilities in Agent Serve: Temperature 0-2, Tool choice, Structured outputs, Max output 131k.

Best for long-context retrieval, large documents, and high-memory workflows. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.