跳转到主要内容

Hy4 flash

TencentUnknown

描述

Hy4 flash is Tencent Hy's most cost-effective Hy model, announced on 2026-11-16 (API id hy4-flash). It has 224 billion total parameters, including 64 billion Engram parameters, with 12 billion active parameters per token. Like Hy4, it is natively multimodal and has a 1,048,576-token context window (Tencent Cloud TokenHub documents 960K max input and 64K max output). Official TokenHub USD list pricing, from Tencent Cloud documentation https://www.tencentcloud.com/document/product/1300/78937, is $0.070 per million input tokens, $0.281 per million output tokens, and $0.003 per million cached input tokens. That same pricing notice offers 50% off Hy4 flash list API pricing until 12:00 Beijing time on 2026-11-30 (11:00 PM ET on 2026-11-29). The official research page also says WorkBuddy access is free until 30 November. Tencent says Hy4 flash will launch on OpenRouter soon and that it plans to open-source the model; no release date was given for the weights, and neither the OpenRouter listing nor the weights were published at catalog time. Tencent's evaluation emphasizes its internal WorkIndex benchmark and a WorkBuddy blind test, and the launch page also reports self-reported scores on public agent and multimodal benchmarks in an official appendix, evaluated at the highest available reasoning setting.

发布日期
2026-11-16
参数规模
224.0B
上下文长度
1.0M
支持模态
image, text

能力雷达图

50
general
30
coding
60
reasoning
51
science估算
40
agents
70
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
智能体能力模型榜124
37.0
LS
多模态榜90
47.0
LS

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

AutomationBench v1.0.652.2%自报
Program Bench16.0%自报

Code

DeepSWE 1.164.6%自报

Multimodal

OSWorld 2.1 (partial)68.1%自报

Reasoning

APEX-Agents63.1%自报
Humanity's Last Exam (with tools)55.2%自报
Terminal-Bench 4.019.2%自报

Vision

MMMU-Pro75.8%自报
ZEROBench0.46 / 100自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Math
60
Multimodal
60
Vision
60
Reasoning
50
General
50
Agents
50
Tool Calling
40
Code
30

定价

输入价格$0.07 / 1M tokens
输出价格$0.281 / 1M tokens
混合价格(3:1)$0.12275 / 1M tokens
缓存读取价格$0.0015 / 1M tokens

速度

暂无速度数据

供应商价格排行

供应商价格排行

10 个供应商

最便宜: Tencent Cloud最贵: CrossModel
供应商输入输出
1Tencent Cloud最便宜
$0
$0
2OpenRouter
$0.035
$0.1405
3Vercel AI Gateway
$0.035
$0.1405
4Tencent主要
$0.07
$0.281
5Novita AI
$0.07
$0.281
6Kilo Gateway
$0.07
$0.281
7DevPass (LLM Gateway)
$0.07
$0.281
8LLM Gateway
$0.07
$0.281
9Kenari
$0.07143
$0.28571
10CrossModel
$0.08
$0.32

比较该模型在不同 API 供应商之间的定价。

外部链接