F24 SALES / MODEL
Z.ai🇨🇳
GLM 5.2
Z.ai's reasoning model is designed for extended software-engineering tasks and large codebases. It keeps long task histories in context and offers adjustable thinking effort, with sparse attention designed to reduce long-input processing costs.
CONTEXT32K
MAX OUTPUT29K
LAST SCAN23 Oct 2026
Reasoning
Open weights
Text
Free aggregator routes
These are the aggregator routes recorded in the current or last published catalog. Each route keeps its exact model ID and thinking information.
Limits above: Kilo. Available gateway routes are listed below.
Kilo
Info- Thinking
- Supported
Model ID · Kilo API
z-ai/glm-5.2:freeOpenRouter
Info- Thinking
- Supported
- Effort levels
- xhigh · high
- Control
- Can be toggled
- Default
- Enabled
- Default effort
- high
Model ID · OpenRouter API
z-ai/glm-5.2:freeLarpRouter
Info- Thinking
- Not documented
Model ID · LarpRouter API
glm-5.2- Context here
- 1M
- Max output here
- 64K
Model sources
Use it through LiteLLM
Import the current LiteLLM-compatible YAML and use the exact model ID shown above. The catalog is generated from the same reviewed scan data as the download.
Download LiteLLM YAML