Tencent: Hy4 preview
tencent/hy4-preview · TencentNot yet established- Declared family
- Unknown
- Entered catalogue
- 28 August 2026
- Last tested
- 5 October 2026
- Measured signature
- tk_5e7942ae
Tencent: Hy4 preview has a clean measured fingerprint that currently sits alone: no other measured model shares its signature.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counted cleanly, and no other model in the catalogue counts the same way | tk_5e7942ae |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_8d2fc6d5 |
| How much it can read and write | Reads up to 1,048,576 tokens at once, writes up to 64,000 | its own listing |
| Whether it thinks before answering | Reasons when asked to, at high, low, none, high by default | its own listing |
| Who served our requests | SiliconFlow | we measured it, 5 October 2026 |
| Measured twice | The 5 October 2026 reading agreed with the 3 September 2026 reading on every one of the 50 strings clean in both: the tokenizer behind this name held. | 50/50 agree |
Click a row to open the full comparison.
We sent Tencent: Hy4 preview fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.
Overhead subtracted: 21 prompt tokens.
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
defaults: {}