GLM vision model for visual reasoning, documents, and multimodal agents
Details
| Field | Value |
|---|---|
| id | z-ai/glm-4.6v-flash |
| modality | text+image+video->text |
| context_length | 200000 |
| max_output_tokens | 64000 |
| knowledge_cutoff | 2025-01-01 |
| release_date | 2025-12-08 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image, video |
| output_modalities | text |