GLM-4.5 Flash
GLM-4.5 Flash is Zhipu AI's language model with a 128K context window and up to 32K output tokens. A fast, lightweight variant of the GLM-4.5 series from Z AI, optimized for low-latency agentic and tool-use applications.
Capabilities
Input1/5
β
Β·
Β·
Β·
Β·
Output1/5
β
Β·
Β·
Β·
Β·
Capabilities1/13
Β·
Β·
β
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| GLM-4.6V Flash | 128K | β | β | Available | |
| GLM-4.5 Flash | β | 128K | β | β | Current |
| GLM-4.7 Flash Non-Reasoning | β | β | β | β | Available |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| GLM-5V Turbo | β | 203K | $1.20 | $4.00 | |
| GLM-5 Turbo | β | 203K | $1.20 | $4.00 | |
| GLM-5.1 Non-Reasoning | β | β | β | β | β |
| GLM-5 Non-Reasoning | β | β | β | β | β |
| GLM-5 Code | β | β | 200K | $1.20 | $5.00 |
| GLM-4 32B | β | 128K | $0.100 | $0.100 | |
| GLM-4.7 FlashX | β | 200K | $0.060 | $0.400 | |
| GLM-4.7 Non-Reasoning | β | β | β | β | β |
| GLM-4.6 Reasoning | β | β | β | β | β |
| GLM-4.6V Reasoning | β | β | β | β | β |