GLM vision model for visual reasoning, documents, and multimodal agents
Details
| Field | Value |
|---|---|
| id | zai-org/glm-4.5v |
| family | glmv |
| modality | text+video+image->text |
| context_length | 65536 |
| max_output_tokens | 16384 |
| knowledge_cutoff | 2025-04 |
| release_date | 2025-08-11 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, video, image |
| output_modalities | text |