GLM vision model for visual reasoning, documents, and multimodal agents
Details
| Field | Value |
|---|---|
| id | z-ai/glm-5v-turbo |
| family | glm |
| modality | image+text+video->text |
| context_length | 202752 |
| max_output_tokens | 131072 |
| release_date | 2026-04-01 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | image, text, video |
| output_modalities | text |