Zhipu AI · glm family
Faster GLM-5 lane for coding agents that need lower latency
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| Zhipu AI Coding Plan | glm-5-turbo | $0 / 1M | $0 / 1M | 200,000 | 131,072 |
| Cortecs | glm-5-turbo | $1.235 / 1M | $4.118 / 1M | 200,000 | 131,072 |
| Z.AI Coding Plan | glm-5-turbo | $0 / 1M | $0 / 1M | 200,000 | 131,072 |
| Z.AI | glm-5-turbo | $1.2 / 1M | $4 / 1M | 200,000 | 131,072 |
| 302.AI | glm-5-turbo | $0.72 / 1M | $3.2 / 1M | 200,000 | 131,072 |
| NanoGPT | z-ai/glm-5-turbo | $1.2 / 1M | $4 / 1M | 202,800 | 131,072 |
| CrossModel | z-ai/glm-5-turbo | $0.9 / 1M | $3.7 / 1M | 200,000 | 128,000 |
| Kilo Gateway | z-ai/glm-5-turbo | $1.2 / 1M | $4 / 1M | 202,752 | 131,072 |
| OpenRouter | z-ai/glm-5-turbo | $1.2 / 1M | $4 / 1M | 202,752 | 131,072 |
| ZenMux | z-ai/glm-5-turbo | $0.88 / 1M | $3.48 / 1M | 200,000 | 128,000 |
| Merge Gateway | zai/glm-5-turbo | $1.2 / 1M | $4 / 1M | 200,000 | 131,072 |
| Vercel AI Gateway | zai/glm-5-turbo | $1.2 / 1M | $4 / 1M | 202,800 | 131,100 |
Attachments
No
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Temperature
Yes