Why high: an exact fingerprint shared with 3 models.
Tencent: Hy3 preview 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.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 3 other models | tk_2b541395 |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_a0f955bb |
| How much it can read and write | Reads up to 262,144 tokens at onceOpenRouter's listing shows 235,929 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum. | 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 | GMICloud | we measured it, 21 August 2026 |
Click a row to open the full comparison.
We sent Tencent: Hy3 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: 12 prompt tokens.
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortseedtemperaturetool_choicetoolstop_p
defaults: {"temperature":0.9,"top_p":1,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
