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:...

模型概览

模型规格

上下文
262,144 tokens
最大输出
128,000 tokens
架构
text->text
分词器
Other
知识截止时间
暂未提供
内容审核
能力与模态

输入输出

输入
text
输出
text
推理能力

· high · low · none

API

支持的 API 参数

frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
可用提供方

7 个提供方

GMICloud

bf16
上下文
262K
最大输出
236K
输入
$0.126
输出
$0.522
缓存读取
$0.032
缓存写入
暂未提供

Baidu

fp8
上下文
262K
最大输出
236K
输入
$0.132
输出
$0.527
缓存读取
$0.033
缓存写入
暂未提供

Tencent

fp8
上下文
262K
最大输出
128K
输入
$0.132
输出
$0.528
缓存读取
$0.033
缓存写入
暂未提供

DeepInfra

fp8
上下文
262K
最大输出
131K
输入
$0.140
输出
$0.580
缓存读取
$0.035
缓存写入
暂未提供

Novita

unknown
上下文
262K
最大输出
236K
输入
$0.140
输出
$0.580
缓存读取
$0.035
缓存写入
暂未提供

Phala

unknown
上下文
262K
最大输出
236K
输入
$0.150
输出
$0.640
缓存读取
$0.040
缓存写入
暂未提供

AtlasCloud

fp8
上下文
262K
最大输出
131K
输入
$0.200
输出
$0.800
缓存读取
$0.050
缓存写入
暂未提供
tencent

个模型

全部模型
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...

上下文
1.0M
输入
text
输出
text
输入: $0.834输出: $2.50每百万 Token
查看模型详情
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...

上下文
8K
输入
text
输出
text
输入: $0.044输出: $0.177每百万 Token
查看模型详情
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...

上下文
8K
输入
text
输出
text
输入: $0.074输出: $0.295每百万 Token
查看模型详情
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.

上下文
8K
输入
text
输出
text
输入: $0.074输出: $0.295每百万 Token
查看模型详情