Passer au contenu principal

Hy4 flash

TencentUnknown

Description

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.

Date de sortie
2026-11-16
Paramètres
224.0B
Longueur du contexte
1.0M
Modalités
image, text

Radar de capacités

50
general
30
coding
60
reasoning
51
scienceest.
40
agents
70
multimodal

Science est estimé à partir des scores scientifiques de LLM Stats ou du raisonnement lorsque les benchmarks scientifiques dédiés ne sont pas disponibles.

Classements

Domaine#RangScoreSource
Capacité agentique124
37.0
LS
Classement multimodal90
47.0
LS

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Code

DeepSWE 1.164.6%Aut.

Multimodal

OSWorld 2.1 (partial)68.1%Aut.

Reasoning

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

Vision

MMMU-Pro75.8%Aut.
ZEROBench0.46 / 100Aut.

Indices d'évaluation AA

(Artificial Analysis)

Aucune donnée d'évaluation AA disponible

Scores par catégorie LLM Stats

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

Tarification

Prix d'entrée$0.07 / 1M tokens
Prix de sortie$0.281 / 1M tokens
Prix mixte (3:1)$0.12275 / 1M tokens
Prix de lecture cache$0.0015 / 1M tokens

Vitesse

Aucune donnée de vitesse disponible

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

8 fournisseurs

Moins cher: Tencent CloudPlus cher: CrossModel
FournisseurEntréeSortie
1Tencent CloudMoins cher
$0
$0
2OpenRouter
$0.035
$0.1405
3Vercel AI Gateway
$0.035
$0.1405
4TencentPRINCIPAL
$0.07
$0.281
5Novita AI
$0.07
$0.281
6Kilo Gateway
$0.07
$0.281
7Kenari
$0.07143
$0.28571
8CrossModel
$0.08
$0.32

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes