GLM vision model for visual reasoning, documents, and multimodal agents
Details
| Field | Value |
|---|---|
| id | zai-org/autoglm-phone-9b-multilingual |
| modality | text+image->text |
| context_length | 65536 |
| max_output_tokens | 65536 |
| release_date | 2025-12-10 |
| is_open_weights | yes |
| supports_tool_call | no |
| supports_reasoning | no |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |