The Hy3 official version is honed for real-world business scenarios, using a Mixture-of-Experts (MoE) architecture with 295B total parameters and 21B activated parameters. It natively supports a 256K context window and offers multiple thinking modes: no_think (ultra-fast response), think_low (quick thinking), and think_high (deep reasoning), balancing ultra-fast responses, complex reasoning, and invocation cost. Compared with the Preview version, Hy3—based on real business feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and others—focuses on improving the Coding Agent, long-form understanding, multi-turn context continuity, search QA, and complex task execution, performing more stably in reducing hallucinations, improving task completion, and engineering usability. It is better suited to practical scenarios such as frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step Agent workflows.
Hy3 vs Hy4 Preview
Compare Hy3 from Hunyuan and Hy4 Preview from Hunyuan on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Hy4 Preview is Tencent Hunyuan’s large language model for agents, coding, office automation, and complex tool use.Hy4 preview has a total of 770B parameters and 49B active parameters, and is primarily optimized for agent, coding, and productivity scenarios. It strengthens understanding, planning, tool invocation, and sustained execution capabilities for complex tasks. Compared with the previous generation, Hy4 preview further improves multi-step agents, code development, and productivity tasks, offering better task decomposition, context continuity, instruction following, and long-horizon execution. In coding scenarios, it further enhances code understanding, generation, modification, and the handling of complex engineering tasks; in productivity scenarios, it focuses on improving document processing, information analysis, office automation, game development, webpage generation, and cross-tool collaboration. Hy4 preview is suitable for coding agents, complex tool invocation, and various agent workflows that require multi-step planning and sustained execution, providing more reliable task completion for complex real-world business scenarios.
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
Tokens / day
Requests / day
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Throughput (tok/s)
TTFT (s)
Uptime (%)
Cost calculator
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Hy3, Hy4 Preview?
Hy3: $0.62/M output tokens; Hy4 Preview: $2.54/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
Hy3: 5.2s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
Hy3 accepts 256,000 and Hy4 Preview accepts 1,024,000 input tokens. Maximum output per request is 128,000 tokens on Hy3 and 64,000 tokens on Hy4 Preview.
Which one generates tokens faster?
Hy3 at 113.5 tok/s and Hy4 Preview at 18.0 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
Hy3 accepts text input and supports tool calling, function calling, structured outputs, web search, long context and thinking; Hy4 Preview accepts text input and supports tool calling, function calling, structured outputs, web search, long context and thinking.
Can I call Hy3 and Hy4 Preview with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
