Multimodal model for analyzing text, images, documents, and rich media
Details
| Field | Value |
|---|---|
| id | rekaai/reka-edge |
| family | reka |
| modality | image+text+video->text |
| context_length | 16384 |
| max_output_tokens | 16384 |
| release_date | 2026-03-20 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | no |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | image, text, video |
| output_modalities | text |