Z.aiGLM-4
GLM-4.7
A reasoning and coding release with preserved thinking across turns.
Practical use
Practical guidance. When comparing per-turn thinking settings, separate simple responses from complex edits. Keep earlier tool results available so the model can revise its reasoning rather than repeating a failed action.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API, Downloadable |
| Model identifiers | glm-4.7zai-org/GLM-4.7 |
| Reasoning controls | Interleaved, preserved and per-turn thinking.GLM-4.7 model card |
| Licence | MIT.GLM-4.7 model card |
| Access | Still listed for API use.Current Z.ai API catalogue |
Related models
A GLM text release with a 200,000-token context.
Launch date not confirmedAPI · DownloadableA hybrid reasoning model with sparse experts.
Launch date not confirmedAPI · Downloadable- GLM-4-32B-0414
Z.ai · GLM-4
A 32-billion-parameter GLM release from April 2025.
Launch date API · Downloadable