Z.aiGLM-5
GLM-5.1
A GLM release trained for sustained multi-step work.
Practical use
Practical guidance. Evaluate a complete task with several dependencies, not just the first answer. Record where the agent changes its plan after an error, and check whether the final result satisfies the original requirement.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API, Downloadable |
| Model identifiers | glm-5.1zai-org/GLM-5.1 |
| Training focus | The model card describes planning, execution and iterative refinement.GLM-5.1 model card |
| Licence | MIT.GLM-5.1 model card |
| Access | Still listed in the current API catalogue.Current Z.ai API catalogue |
Related models
A text model with stronger post-training on the GLM-5.2 base.
Launch date not confirmedAPI · DownloadableA long-context GLM release with a shared sparse-attention indexer.
Launch date not confirmedAPI · DownloadableA sparse text model for reasoning and software engineering.
Launch date not confirmedAPI · Downloadable