modelgrep
Q

Qwen: Qwen3.6 Max Preview

qwen/qwen3.6-max-preview

13th smartest of 178ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
51.8
13th of 178
Design Elo
Speed
48
174th fastest
Latency
1.5s
first token
Input price
$1.04
211th cheapest
Context
262K
66K max out

How it compares

Smarter than93%
of all ranked models
Faster than41%
of all ranked models
Cheaper than29%
of all ranked models

Overview

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...

Benchmarks

independent · via OpenRouter
Artificial Analysis94th percentile
Intelligence Index
51.8
Coding Index
44.9
Agentic Index
64.8
GPQA Diamond
89%
Humanity's Last Exam
29%
SciCode
47%
Tau²-Bench (agentic)
96%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Alibaba$1.04$6.24100%

Specifications

Context window262K
Max output66K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3.6 Max Preview FAQ

How much does Qwen3.6 Max Preview cost?

Qwen3.6 Max Preview costs $1.04 per million input tokens and $6.24 per million output tokens via OpenRouter, making it 211th cheapest of 298 paid models.

How smart is Qwen3.6 Max Preview?

Qwen3.6 Max Preview scores 51.8 on the Artificial Analysis Intelligence Index, ranking 13th of 178 benchmarked models, with a GPQA Diamond score of 89%.

How fast is Qwen3.6 Max Preview?

Qwen3.6 Max Preview generates around 48 tokens per second with 1.5s time-to-first-token (p50), the 174th fastest tracked model.

What is Qwen3.6 Max Preview's context window?

Qwen3.6 Max Preview supports a 262K-token context window and can output up to 66K tokens. It accepts text input.

Compare head-to-head