Hy4

Hy4

Tencent
+
+

Related Products

  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Checksum.ai
    1 Rating
    Visit Website
  • QuantaStor
    6 Ratings
    Visit Website
  • Lockbox LIMS
    72 Ratings
    Visit Website
  • Bitdefender Ultimate Small Business Security
    5 Ratings
    Visit Website
  • AddSearch
    140 Ratings
    Visit Website
  • Pipefy
    592 Ratings
    Visit Website
  • Visual Planning
    117 Ratings
    Visit Website
  • Dialpad Support
    1,600 Ratings
    Visit Website
  • Orca Security
    606 Ratings
    Visit Website

About

Hy4 preview is a new-generation open source Mixture-of-Experts flagship model built for real-world productivity tasks across software engineering, office work, game development, and scientific research. The model contains 770B total parameters with 49B activated per token and supports a 1M-token context window, giving it the capacity to work through large codebases, extensive document collections, and long multi-step tasks. Its 78-layer architecture combines Gated DeepSeek Sparse Attention with IndexCache for cross-layer sparse index reuse and identity Hyper-Connections to expand information flow between layers. A native Multi-Token Prediction layer is included for speculative decoding. Hy4 preview is designed to understand, plan, debug, and verify long-horizon engineering tasks, with additional gains in front-end visual quality and interaction design.

About

Muse Spark 1.3 is an AI model with improved performance across agentic and coding tasks, designed to be smarter and more practical for real-world work. It sustains longer-horizon tasks by collaborating with users and managing multiple workflows in a single, long thread. Given an open-ended objective, it uses tools to build context across messy or conflicting sources, correct gaps in its plan, track what it has learned, and produce a final deliverable. It asks clarifying questions when prompts are ambiguous, requests help when stuck, and confirms before taking consequential actions. The model follows complex, long-form instructions more reliably, preserving detailed requirements across multi-step tasks without dropping constraints or drifting from the requested workflow. Improved multitasking allows it to map incoming prompts to the correct task even when users interrupt or redirect previous requests.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Developers, researchers, and technical professionals seeking an AI model for coding, document work, game development, scientific reasoning, and complex productivity tasks

Audience

Developers and professional users seeking an AI model for complex agentic workflows, long-running tasks, coding, and multi-step work requiring reliable instruction following

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

No information available.
Free Version
Free Trial

Pricing

$1.25 per 1M tokens (input)
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 5.0 / 5
ease 5.0 / 5
features 5.0 / 5

Pros & Cons from Real Users

Pros

  • This feels like the version where Muse Spark becomes much more interesting for developers. The focus is not just “better chat,” but better coding, better agentic workflows, and more reliable long-running tasks. The biggest win is efficiency. Meta says Muse Spark 1.3 uses fewer tokens and fewer tool calls on coding tasks, which matters a lot if you are running agents repeatedly instead of asking one-off questions. I also like that it is available in both Muse Code and the Meta Model API. That gives developers a practical path whether they want a coding-agent experience or want to plug the model into their own workflows.

Cons

  • Have not found any downsides thus far. This model is a big leap for Meta

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Tencent
Founded: 1998
China
hy.tencent.ai/research/hy4-preview

Company Information

Meta
Founded: 2004
United States
meta.ai/

Alternatives

Alternatives

GPT-5.6 Sol

GPT-5.6 Sol

OpenAI
GPT-5.6 Sol

GPT-5.6 Sol

OpenAI

Categories

Categories

Integrations

C#
C++
Cheaper Inference
Continue
Dart
Go
Gray Swan
Java
JavaScript
Kubernetes
LlamaIndex
Muse Code
Muse Spark
Muse Video
Objective-C
PHP
Python
SQL
Scala
Vercel AI SDK

Integrations

C#
C++
Cheaper Inference
Continue
Dart
Go
Gray Swan
Java
JavaScript
Kubernetes
LlamaIndex
Muse Code
Muse Spark
Muse Video
Objective-C
PHP
Python
SQL
Scala
Vercel AI SDK
Claim Hy4 and update features and information
Claim Hy4 and update features and information
Claim Muse Spark 1.3 and update features and information
Claim Muse Spark 1.3 and update features and information