Models

hy3 vs qwen3.8-max-preview

Output tokens cost $0.62 per million on hy3 and $1.01 per million on qwen3.8-max-preview. Input tokens cost $0.16 per million on hy3 and $0.34 per million on qwen3.8-max-preview. Cached input tokens are billed at $0.04 per million on hy3 and $0.03 per million on qwen3.8-max-preview. Context lengths are 256,000 tokens on hy3 and 983,616 tokens on qwen3.8-max-preview. Time to first token (TTFT) measured on AIHubMix is 3.7s on hy3 and 2.4s on qwen3.8-max-preview. Measured output throughput is 26.5 tok/s on hy3 and 48.1 tok/s on qwen3.8-max-preview. On the LMArena coding leaderboard hy3 scores 1503 and qwen3.8-max-preview scores 1528.

Hunyuanhy3Qwenqwen3.8-max-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$0.16 /M
Output$0.62 /M
Qwen logo
qwen3.8-max-preview
Qwen · text, image → text

Qwen 3.8 Max Preview(Qwen3.8-Max-Preview) is the latest-generation foundation model in the Qwen family, packing 2.4T parameters and still evolving. Compared with the previous flagship Qwen 3.7 Max, it delivers major gains in core capabilities like Coding and Cowork (professional productivity), with world-leading performance on complex, long-horizon tasks such as full-stack development, data analysis, and Office workflows. Launch offer: Credits are consumed at just 20% of the standard rate, effectively 5× your usage. Limited time only.

Input$0.34 /M
Output$1.01 /M

Pricing & Specifications

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

hy3
qwen3.8-max-preview
Input /M
$0.16
$0.34
Output /M
$0.62
$1.01
Cache read /M
$0.04
$0.03
Context length
256,000
983,616
Max output
128,000
131,072
Time to First Token
3.7 s
2.4 s
Throughput
26.5 tok/s
48.1 tok/s
Modalities
text
textimage
Supported Parameters
toolsfunction callingstructured outputsweblong contextthinking
toolsfunction callingstructured outputsweblong contextthinking
API Formats

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.

hy3qwen3.8-max-preview

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

hy3qwen3.8-max-preview

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
hy3qwen3.8-max-preview
1400146015201580
Overall
14571490
Coding
15031528
Math
14811513
Hard prompts
14751516
Instruction following
14451484
Multi-turn
14631506
Creative writing
14331483
Longer query
14691509
Chinese
15181557
English
14701493
WebDev Arena
hy3qwen3.8-max-preview
14401520160016801760
Overall
15241670
React
15371680
HTML
14631628
Gaming
15601740
Simulations
15511665
Data analytics
14891614

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
$18.74 /mo
qwen3.8-max-preview
$35.49 /mo

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

FAQ

Which is cheaper: hy3, qwen3.8-max-preview?

hy3: $0.62/M output tokens; qwen3.8-max-preview: $1.01/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

qwen3.8-max-preview: 1528; hy3: 1503 (LMArena coding leaderboard).

Which responds faster?

qwen3.8-max-preview: 2.4s 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 qwen3.8-max-preview accepts 983,616 input tokens. Maximum output per request is 128,000 tokens on hy3 and 131,072 tokens on qwen3.8-max-preview.

Which one generates tokens faster?

qwen3.8-max-preview at 48.1 tok/s and hy3 at 26.5 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; qwen3.8-max-preview accepts text and image input and supports tool calling, function calling, structured outputs, web search, long context and thinking.

Can I call hy3 and qwen3.8-max-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.