Models

Hy3 vs Hy3 Preview

Compare Hy3 from Hunyuan and Hy3 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.

HunyuanHy3HunyuanHy3 Preview
Hunyuan logo
Hy3
Hunyuan · text → text

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.

Input$0.1562 /M
Output$0.6248 /M
Cache read$0.0391 /M
Hunyuan logo
Hy3 Preview
Hunyuan · text → text

Hunyuan Hy3 preview is designed for agent workloads, adopting a MoE architecture with 295B capacity and 21B activated parameters. It provides three modes within the same model—no_think (ultra-fast response), think_low (fast thinking), and think_high (deep reasoning)—to accommodate different latency and depth requirements from high-frequency interactions to complex engineering tasks. On code benchmarks such as SWE-bench Verified it approaches the current state of the art, and its 256K context supports cross-file code refactoring and long-document analysis. It is suitable for developers who require reliable task completion while being sensitive to inference costs.

Input$0.17 /M
Output$0.5667 /M
Cache read$0.051 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

Hy3
Hy3 Preview
Input /M
$0.1562
$0.17
Output /M
$0.6248
$0.5667
Cache read /M
$0.0391
$0.051
Context length
256,000
256,000
Max output
128,000
128,000
Time to First Token
4.0 s
2.1 s
Throughput
63.2 tok/s
40.2 tok/s
Modalities
text
text
Supported Parameters
toolsfunction callingstructured outputsweblong contextthinking
toolsfunction callingstructured outputsweblong contextthinking
API Formats
Released
-
April 23, 2026

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.

hy3hy3-preview

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

hy3hy3-preview

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
hy3hy3-preview
1400144014801520
Overall
14551455
Coding
15021502
Math
14751475
Hard prompts
14751475
Instruction following
14451445
Multi-turn
14571457
Creative writing
14231423
Longer query
14661466
Chinese
15171517
English
14681468
WebDev Arena
hy3hy3-preview
1440148015201560
Overall
15121512
React
15181518
HTML
14771477
Gaming
15441544
Simulations
15381538
Data analytics
14651465

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

Hy3 Preview
$18.70 /mo
Hy3
$18.74 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: Hy3, Hy3 Preview?

Hy3 Preview: $0.5667/M output tokens; Hy3: $0.6248/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Hy3: 1502; Hy3 Preview: 1502 (LMArena coding leaderboard).

Which responds faster?

Hy3 Preview: 2.1s 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 Hy3 Preview accepts 256,000 input tokens. Maximum output per request is 128,000 tokens on Hy3 and 128,000 tokens on Hy3 Preview.

Which one generates tokens faster?

Hy3 at 63.2 tok/s and Hy3 Preview at 40.2 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; Hy3 Preview accepts text input and supports tool calling, function calling, structured outputs, web search, long context and thinking.

Can I call Hy3 and Hy3 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.