← Models

Qwen3.6 Plus Preview (free) vs Qwen3.8 Max

Compare Qwen3.6 Plus Preview (free) from Qwen and Qwen3.8 Max from Qwen on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.

QwenQwen3.6 Plus Preview (free)QwenQwen3.8 Max
Qwen logo
Qwen3.6 Plus Preview (free)
Qwen · text → text

This model has been removed from the platform.

Input$0 /M
Output$0 /M
Qwen logo
Qwen3.8 Max
Qwen · text, image, video → text

Qwen3.8-Max is Alibaba Cloud Tongyi Qianwen's next-generation flagship large language model, featuring a mixture-of-experts (MoE) architecture with 2.4 trillion parameters. It achieves another breakthrough in encoding depth, enabling it to handle more complex engineering-grade projects and long-term autonomous development; collaborative agent capabilities are significantly enhanced, performing more confidently in multi-tool orchestration and end-to-end delivery; visual understanding is comprehensively improved, with more sensitive and accurate chart reasoning, document parsing, and multimodal perception. Continuing the 1-million-context window, reasoning modes, and a complete tool ecosystem, it continues to evolve at a higher level of intelligence.

Input$1.69 /M
Output$5.07 /M
Cache read$0.169 /M

Pricing & Specifications

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

Qwen3.6 Plus Preview (free)
Qwen3.8 Max
Input
$0 /M
$1.69 /M
Output
$0 /M
$5.07 /M
Cache read
-
$0.169 /M
Context length
1,000,000
1,000,000
Max output
65,535
131,072
Time to First Token
-
4.7 s
Throughput
-
27.2 tok/s
Modalities
text
textimagevideo
Supported Parameters
thinkinglong context
toolsfunction callingstructured outputsweblong contextthinking
API Formats
Released
-
August 3, 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.

qwen3.6-plus-preview-freeqwen3.8-max

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

qwen3.6-plus-preview-freeqwen3.8-max

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
qwen3.6-plus-preview-freeqwen3.8-max
1380144015001560
Overall
14441484
Coding
14931524
Math
14571504
Hard prompts
14661506
Instruction following
14381478
Multi-turn
14411495
Creative writing
14061471
Longer query
14541495
Chinese
14881541
English
14571493
WebDev Arena
qwen3.6-plus-preview-freeqwen3.8-max
1420152016201720
Overall
14631670
React
14571679
HTML
14681628
Gaming
14711732
Simulations
14751676
Data analytics
14441616

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.

Qwen3.6 Plus Preview (free)
$0.00 /mo
Qwen3.8 Max
$177 /mo

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

FAQ

How do their coding arena scores compare?

Qwen3.8 Max: 1524; Qwen3.6 Plus Preview (free): 1493 (LMArena coding leaderboard).

How large is each context window?

Qwen3.6 Plus Preview (free) accepts 1,000,000 and Qwen3.8 Max accepts 1,000,000 input tokens. Maximum output per request is 65,535 tokens on Qwen3.6 Plus Preview (free) and 131,072 tokens on Qwen3.8 Max.

What inputs and capabilities does each model support?

Qwen3.6 Plus Preview (free) accepts text input and supports thinking and long context; Qwen3.8 Max accepts text, image and video input and supports tool calling, function calling, structured outputs, web search, long context and thinking.

Can I call Qwen3.6 Plus Preview (free) and Qwen3.8 Max 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.