Tencent Hy reasoning model for coding, instruction following, and agent tasks
Details
| Field | Value |
|---|---|
| id | hy3 |
| family | Hy |
| modality | text->text |
| context_length | 256000 |
| max_input_tokens | 192000 |
| max_output_tokens | 128000 |
| release_date | 2026-07-06 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | no |
| supports_attachment | no |
| input_modalities | text |
| output_modalities | text |