LLM Reference

Hunyuan Hy4 Preview

Released
2026-08-28
Last refreshed
2026-08-31
Status
Researched today
Open sourceCommercial use: permittedCodingRAGAgentsLong contextJSON / Tool useAgentCoding

Hunyuan Hy4 Preview is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1.05m context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Hunyuan
Released
2026-08-28
Context
1.05m
Parameters
770B (49B active)
Architecture
Mixture of Experts
Specialization
agentic
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by

AI innovations for societal improvement

Shenzhen, China
Founded 2016
Website
Pricing
Output / 1M
$2.50
Input / 1M
$0.834

Cheapest of 2 routes · OpenRouter · cache read $0.042

About

Tencent Hunyuan Hy4 preview is a Mixture-of-Experts flagship language model released and open-sourced August 28, 2026. First-party Tencent release: 770B total parameters with 49B activated per token, context window exceeding 1M tokens, aimed at coding, office productivity, game development, and scientific research. Hugging Face model card (tencent/Hy4-preview) documents a 78-layer MoE backbone (256 routed experts, top-8 plus 1 shared expert), Gated DeepSeek Sparse Attention with IndexCache, iHC residual streams, native MTP speculative decoding, Apache License 2.0 weights (also Hy4-preview-FP8), and OpenAI-compatible serving via vLLM/SGLang with tool-call and reasoning parsers.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenRouter$0.834$2.50read $0.042
Serverless
Tencent Cloud TI Platform$0.834$2.50read $0.042
Serverless

Capabilities

ReasoningJSON / Tool usePrompt CachingFine-tuning

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

hy4-preview