GLM-4.5-Flash
Open weightsZ.AI · Efficient GLM model for fast reasoning, coding, and agent workflows
Key facts
- Provider
- Z.AI
- Context window
- 131.1K tokens
- Max output
- 98.3K tokens
- Input price
- Free / M tok
- Output price
- Free / M tok
- Knowledge cutoff
- Apr 2025
- Released
- Jul 28, 2025
- License
- Open weights
Capabilities
ReasoningTool callingStructured outputFile attachmentsTemperature controlOpen weights
Reasoning options
- toggle
Pricing
USD per million tokens, list API rates.
- Input
- Free
- Output
- Free
- Cache read
- Free
- Cache write
- Free
Modalities
- Input
- Text
- Output
- Text