Hy3

Hy3

Tencent
Laguna S 2.1

Laguna S 2.1

Poolside
+
+

Related Products

  • Gemini Enterprise Agent Platform
    984 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Coevera
    752 Ratings
    Visit Website
  • Google AI Studio
    30 Ratings
    Visit Website
  • NetBrain
    274 Ratings
    Visit Website
  • Dialpad Support
    1,588 Ratings
    Visit Website
  • Iru
    1,351 Ratings
    Visit Website
  • Epicor Connected Process Control
    4 Ratings
    Visit Website
  • Runpod
    220 Ratings
    Visit Website
  • Denodo
    387 Ratings
    Visit Website

About

Hy3 preview is Tencent Hy’s most intelligent model in the Hy series to date, built as a 295B-parameter Mixture-of-Experts model with 21B activated parameters, 3.8B MTP layer parameters, and support for up to a 256K token context window. As the first model trained on Tencent Hy’s rebuilt infrastructure, Hy3 preview is designed to improve real-world usability across complex reasoning, instruction following, context learning, coding, agent capabilities, and overall inference performance. It integrates both fast and slow thinking capabilities, allowing direct responses for simpler tasks and deeper reasoning for complex math, coding, and reasoning work. The model is built around well-rounded capabilities across long-context understanding, instruction following, tool use, and agent workflows, with evaluation focused not only on standard benchmarks but also on authentic business and development scenarios.

About

Laguna S 2.1 is an open weight agentic coding model designed to pursue longer-horizon work and make effective use of reasoning. It uses a 118-billion-parameter Mixture-of-Experts architecture with 8 billion active parameters per token and supports a context window of up to one million tokens in both thinking and no-thinking modes. Its compact active size makes it suitable for complex work on local machines while remaining competitive with models many times larger on terminal, software-engineering, codebase-question-answering, and tool-use benchmarks. Laguna S 2.1 is built to keep working through difficult tasks with greater persistence, verification, and willingness to backtrack instead of declaring success too early. In demonstrated runs, it built and validated a browser rendering engine from an empty folder, optimized an agent harness for faster execution and substantially lower memory allocation, and completed extended mathematical research using the tools in its environment.

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

AI labs and agent-framework developers who need a large reasoning model for coding, tool use, long-context tasks, and real-world agent workflows

Audience

Private AI infrastructure teams that need a compact, self-hostable model for long-running coding and software-engineering agents

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

Free
Free Version
Free Trial

Pricing

No information available.
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 4.0 / 5
design 5.0 / 5

Pros & Cons from Real Users

Pros

  • Laguna S 2.1 looks awesome from a developer’s point of view because it is built specifically for agentic coding, not just general chatbot tasks. I like that it is open-weight, relatively compact for its capability, and designed for the kind of workflows where an AI needs to inspect a repo, reason through changes, edit code, and keep moving across multiple steps. The 1M-token context window is a huge plus. For real engineering work, context is everything: source files, docs, logs, tests, tickets, configs, and previous attempts all matter. Having a coding model that can handle that much context makes it much more useful for serious repo-level work.

Cons

  • It is still new, so I would want to test it heavily before trusting it with production code. Coding benchmarks are useful, but the real test is messy repos, weird dependencies, flaky tests, security-sensitive changes, and long-running agent loops.

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Tencent
Founded: 1998
China
hy.tencent.com/research/hy3-preview

Company Information

Poolside
Founded: 2023
United States
poolside.ai/blog/introducing-laguna-s-2-1

Alternatives

Big Pickle

Big Pickle

OpenCode Zen

Alternatives

Claude Fable 5

Claude Fable 5

Anthropic
Claude Fable 5

Claude Fable 5

Anthropic
Claude Opus 5

Claude Opus 5

Anthropic
Claude Opus 4.8

Claude Opus 4.8

Anthropic
Laguna XS 2.1

Laguna XS 2.1

Poolside
LongCat-2.0

LongCat-2.0

LongCat

Categories

Categories

Integrations

Agent Client Protocol (ACP)
Claude Code
Cline
Hermes Agent
Hugging Face
IntelliJ IDEA
Kilo Code
Nous Portal
Ollama
OpenAI Codex
OpenClaw
OpenCode
OpenRouter
Poolside
Roo Code
Tencent Hy
Visual Studio
Visual Studio Code
Zed

Integrations

Agent Client Protocol (ACP)
Claude Code
Cline
Hermes Agent
Hugging Face
IntelliJ IDEA
Kilo Code
Nous Portal
Ollama
OpenAI Codex
OpenClaw
OpenCode
OpenRouter
Poolside
Roo Code
Tencent Hy
Visual Studio
Visual Studio Code
Zed
Claim Hy3 and update features and information
Claim Hy3 and update features and information
Claim Laguna S 2.1 and update features and information
Claim Laguna S 2.1 and update features and information