Model Positioning and Release Date
GLM-Z1-Flash is a free reasoning model in the GLM-Z1 series, intended to lower the barrier to using reasoning models. The official release record is dated 2025-04-14. (docs.bigmodel.cn)
Capabilities and Uses
- Deep thinking is enabled by default, targeting tasks such as mathematical and logical reasoning, long-document analysis, and code generation.
- Official documentation lists support for streaming output, Function Calling, structured output such as JSON, and MCP tool calling.
- Applications presented by the official source include data reasoning, matching people to jobs, script generation, and professional report writing; generated content still requires human verification. (docs.bigmodel.cn)
Limitations and Status
The official model documentation states that the GLM-Z1 series has been taken offline; historical statements that it was free should not be treated as a guarantee that it is currently available for use. The pricing table lists the model's context as 128K tokens. The model documentation mentions context caching, but the domestic pricing table marks cache hits as unsupported for this model; actual support is subject to the platform. (docs.bigmodel.cn)
Pricing
- Historical list price on the domestic Zhipu Open Platform: Input free and output free in Chinese yuan (CNY); the pricing table's unit of measurement is per million tokens. Cache storage is marked as free for a limited time, and cache hits are marked as unsupported. This list price does not change the model's offline status. (docs.bigmodel.cn)
- The official international-site pricing page was also consulted; no USD price for this model was found, and no price is inferred or added. (docs.z.ai)
Official Sources
- Model and Product Release Records
- GLM-Z1-Flash Model Documentation
- Domestic API Pricing
- International Site API Pricing
Date consulted: 2026-11-18.