Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Details
| Field | Value |
|---|---|
| id | moonshotai/Kimi-K2.6-TEE |
| family | kimi-k2 |
| modality | text+image+video->text |
| context_length | 262144 |
| max_output_tokens | 65535 |
| quantization | int4 |
| knowledge_cutoff | 2025-12 |
| release_date | 2026-04-21 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, image, video |
| output_modalities | text |