Multimodal model for analyzing text, images, documents, and rich media
Details
| Field | Value |
|---|---|
| id | minicpm-v-4.5 |
| modality | text+image->text |
| context_length | 32000 |
| max_output_tokens | 32000 |
| release_date | 2025-08-26 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | no |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image |
| output_modalities | text |