GLM 5.2 Short Flex
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
Model facts
- Context window
- 2K tokens
- Maximum output
- 32K tokens
- Cheapest paid input
- $0.943 per 1M tokens
- Cheapest paid output
- $2.92 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, temperature control, open weights, text.
Observed price history
- 2026-08-24: $0.725 input / $2.25 output per 1M tokens
- 2026-08-28: $0.943 input / $2.92 output per 1M tokens
API providers
- Neuralwatt — model id glm-5.2-short-flex; $0.943 input / $2.92 output per 1M tokens; provider documentation