Tencent: Hy3 is Tencent's model, and its measured tokenizer sits in Tencent's own signature group alongside its sibling models. No other maker's measured model shares it so far.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 3 other models | tk_2b541395 |
| API surface | No other entry shares this exact contract | api_14e1b3d2 |
| Context and output | 262,144 context · 128,000 max output | declared |
| Reasoning contract | Optional · efforts high, low, none · default high | declared |
| Serving providers observed | Phala | measured 21 August 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 12 prompt tokens.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
defaults: {"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for Tencent: Hy3: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
