Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
| Attribute | glm-5-turbo |
|---|---|
| Pricing | |
| Input | $0.96 / 1M |
| Output | $3.20 / 1M |
| Cache Write (5m) | $0.96 / 1M Default rate |
| Cache Write (1h) | $0.96 / 1M Default rate |
| Cache Read | $0.96 / 1M Default rate |
| Web Search | No surcharge |
| Context | |
| Max context | 202.8K |
| Max output | Unknown |
| Capabilities | |
| Vision | No |
| Function Calling | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Catalogue | |
| Provider | Z.AI |
| Category | chat |
| Charge type | Pay As You Go |
| Released | — |
| Description | |
| Summary | GLM 5 Turbo is Z.AI's language model that takes text input and returns text. It supports a reasoning mode, tool calling and structured JSON output. |