tencent logo
tencent

Tencent: Hy3

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:...

개요

모델 사양

Context
262,144 tokens
최대 출력
128,000 tokens
아키텍처
text->text
토크나이저
Other
지식 기준일
Not provided
검토됨
아니요
기능 및 모달리티

InputOutput

Input
text
Output
text
추론

· high · low · none

API

지원 API 매개변수

frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
사용 가능한 제공업체

7 개 제공업체

GMICloud

bf16
Context
262K
최대 출력
236K
Input
$0.126
Output
$0.522
캐시 읽기
$0.032
캐시 쓰기
Not provided

Baidu

fp8
Context
262K
최대 출력
236K
Input
$0.132
Output
$0.527
캐시 읽기
$0.033
캐시 쓰기
Not provided

Tencent

fp8
Context
262K
최대 출력
128K
Input
$0.132
Output
$0.528
캐시 읽기
$0.033
캐시 쓰기
Not provided

DeepInfra

fp8
Context
262K
최대 출력
131K
Input
$0.140
Output
$0.580
캐시 읽기
$0.035
캐시 쓰기
Not provided

Novita

unknown
Context
262K
최대 출력
236K
Input
$0.140
Output
$0.580
캐시 읽기
$0.035
캐시 쓰기
Not provided

Phala

unknown
Context
262K
최대 출력
236K
Input
$0.150
Output
$0.640
캐시 읽기
$0.040
캐시 쓰기
Not provided

AtlasCloud

fp8
Context
262K
최대 출력
131K
Input
$0.200
Output
$0.800
캐시 읽기
$0.050
캐시 쓰기
Not provided
tencent

models

모든 모델
tencent logotencent

Tencent: Hy4 preview

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...

Context
1.0M
Input
text
Output
text
Input: $0.834Output: $2.50per 1M tokens
모델 상세 보기
tencent logotencent

Tencent: Hy-MT2-1.8B

Hy-MT2-1.8B is a compact 1.8B-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...

Context
8K
Input
text
Output
text
Input: $0.044Output: $0.177per 1M tokens
모델 상세 보기
tencent logotencent

Tencent: Hy-MT2-30B-A3B

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

Context
8K
Input
text
Output
text
Input: $0.074Output: $0.295per 1M tokens
모델 상세 보기
tencent logotencent

Tencent: Hy-MT2-7B

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.

Context
8K
Input
text
Output
text
Input: $0.074Output: $0.295per 1M tokens
모델 상세 보기