← Models

Qwen3.5 122B A10B vs Qwen3.8 Max

Compare Qwen3.5 122B A10B 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.

QwenQwen3.5 122B A10BQwenQwen3.8 Max
Qwen logo
Qwen3.5 122B A10B
Qwen · text, image, video → text

The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.

Input$0.1126 /M
Output$0.9008 /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.

Qwen3.5 122B A10B
Qwen3.8 Max
Input
$0.1126 /M
$1.69 /M
Output
$0.9008 /M
$5.07 /M
Cache read
-
$0.169 /M
Context length
262,144
1,000,000
Max output
65,536
131,072
Time to First Token
0.6 s
4.7 s
Throughput
108.6 tok/s
27.2 tok/s
Modalities
textimagevideo
textimagevideo
Supported Parameters
toolsfunction callingstructured outputsweblong contextthinking
toolsfunction callingstructured outputsweblong contextthinking
API Formats
Released
February 23, 2026
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.

qwen3.5-122b-a10bqwen3.8-max

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

qwen3.5-122b-a10bqwen3.8-max

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
qwen3.5-122b-a10bqwen3.8-max
1340140014601520
Overall
14161484
Coding
14581524
Math
14251504
Hard prompts
14331506
Instruction following
14061478
Multi-turn
14191495
Creative writing
13651471
Longer query
14181495
Chinese
14571541
English
14311493
Vision
qwen3.5-122b-a10bqwen3.8-max
12001240128013201360
Overall
12261299
OCR
12391316
Diagram
12441321
Homework
12531334
WebDev Arena
qwen3.5-122b-a10bqwen3.8-max
1300142015401660
Overall
13601670
React
13511679
HTML
13521628
Gaming
13511732
Simulations
13271676
Data analytics
13501616

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.

Qwen3.5 122B A10B
$20.27 /mo
Qwen3.8 Max
$177 /mo

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

FAQ

Which is cheaper: Qwen3.5 122B A10B, Qwen3.8 Max?

Qwen3.5 122B A10B: $0.9008/M output tokens; Qwen3.8 Max: $5.07/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Qwen3.8 Max: 1524; Qwen3.5 122B A10B: 1458 (LMArena coding leaderboard).

Which responds faster?

Qwen3.5 122B A10B: 0.6s 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?

Qwen3.5 122B A10B accepts 262,144 and Qwen3.8 Max accepts 1,000,000 input tokens. Maximum output per request is 65,536 tokens on Qwen3.5 122B A10B and 131,072 tokens on Qwen3.8 Max.

Which one generates tokens faster?

Qwen3.5 122B A10B at 108.6 tok/s and Qwen3.8 Max at 27.2 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Qwen3.5 122B A10B accepts text, image and video input and supports tool calling, function calling, structured outputs, web search, long context and thinking; 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 Qwen3.5 122B A10B 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.