Tencent: Hy-MT2-7B

tencent/hy-mt2-7b · TencentNot yet established

Tokenizer group (measured): Tencent
Evidence confidence: Moderate
Declared tokenizer tag: Other
Entered catalogue: 19 August 2026
Last tested: 3 September 2026
Measurement: Measured

Evidence

✓ near-exact agreement (49/50) with tencent/hunyuan-a13b-instruct

Compare with Tencent: Hunyuan A13B Instruct

Download JSON Report a correction

Identity statement

Tencent: Hy-MT2-7B 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.

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Clean measurement; no exact match yet	tk_70a22c4f
API surface	Identical contract to 1 other entry	api_797564b9
Context and output	8,192 context · 4,096 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	Tencent	measured 3 September 2026

Closest measured models

Agreement across the mutually clean test strings

Tencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instruct49/50 · 98%Perceptron: Perceptron Mk1perceptron/perceptron-mk130/50 · 60%Kwaipilot: KAT-Coder-Pro V2kwaipilot/kat-coder-pro-v230/50 · 60%Morph: Morph V3 Largemorph/morph-v3-large30/50 · 60%OpenAI: GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instruct24/41 · 59%Xiaomi: MiMo-V2.5xiaomi/mimo-v2.528/50 · 56%

Click a row to open the full comparison.

The measured fingerprint

Marginal prompt-token cost of each test string, grouped by script

All 50 rows

English and whitespace

en-prose14

en-long16

spaces-203

spaces-603

tabs-203

newlines-204

mixed-ws5

Digits

digits-99

digits-1212

digits-3030

digits-sep12

float-long22

CJK

zh-common9

zh-long10

zh-rare18

ja-kana13

ja-kanji13

ko19

Other scripts

ru16

ar25

he24

hi32

th25

el28

Emoji

emoji-basic10

emoji-skin19

emoji-zwj-family11

emoji-zwj-x333

emoji-flags24

emoji-prof22

Rare Unicode

math29

boxdraw26

combining12

cjk-ext-b13

surrogates40

zalgo35

rtl-mix11

Code

py-code25

py-indent15

json25

html16

regex44

camel5

snake6

Repetition and encodings

rare-word-x531

repeat-tok22

base6436

hex17

url19

uuid36

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 2 prompt tokens.

Declared record

What the catalogue claims about this model

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

Modalities: text->text
Declared tokenizer: Other
Prompt price: $0.07 / M tokens
Completion price: $0.29 / M tokens

Supported parameters

max_completion_tokensmax_tokensresponse_formatstopstructured_outputstemperature

defaults: {}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

19 August 2026Enters the OpenRouter catalogue with no declared family.
3 September 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
3 September 2026YFarmX assessment: consistent with the Tencent family, moderate confidence.

Cite this page as the evidence record for Tencent: Hy-MT2-7B: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.