Qwen 3.6 Max Preview

qwen/qwen3.6-max-preview

vibe coding & efficient agent execution.

cmd --model qwen/qwen3.6-max-preview
Intelligence index
41.1
Output speed
not yet scored
Input
$1.30 /M
Output
$7.80 /M
Cache read
$0.26 /M
Agent-loop cost
$0.57 /M in
Context window
200K tokens
Released
April 20, 2026
Modalities

vs. the lineup

Qwen 3.6 Max Preview beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingSpeedInput $/MOutput $/MBlended $/MContext
Qwen 3.7 Max46.766$2.50$7.50$3.751M
Qwen 3.6 Max Preview41.1$1.30$7.80$2.92200K
Qwen 3.6 Plus40.554.5$0.50$3$1.13200K
Qwen 3.7 Plus39.455.954.9$0.40$1.60$0.701M
Qwen 3.8 Max$2$6$31M
Qwen 3.7 Flash$0.03$0.13$0.061M
DeepSeek V4 Pro (latest)pinned45.359.463.3$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned5269.1115.9$0.22$0.66$0.331M

coding performance

The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for Qwen 3.6 Max Preview has been left empty.

IFBench
76.6
instruction following
Intelligence Index
41.1
#31 of 46 scored
Long-context reasoning
72
reasoning across a long context
SciCode
46.9
scientific coding
GPQA Diamond
88.8
graduate-level QA

usage calculator

How far a month of credits goes on Qwen 3.6 Max Preview.

Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.015 · in $1.30 · out $7.80 · cache $0.26 per M
fresh input 7%output 9%cache reads 84%
Requests / 30 days
648
$10 credits ÷ $0.015 per request
~130 quick fixes~26 bug fixes~4 feature PRs

what real work costs

Real coding tasks priced end to end on Qwen 3.6 Max Preview, from a quick lookup to a full-repo agent run.

One agent task
$0.19
180K in at 75% cache hit, 12K out
What you pay
$0.98 /M
all-in across every token that task touched
Sticker input
$1.30 /M
cache reads bill at $0.26 /M instead
TaskTokens in · outQwen 3.6 Max PreviewMuse Spark 1.2Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.01$0.0063$0.0065
Review a 500-line PR60K · 4K$0.07$0.05$0.04
Fix a bug (agent loop)180K · 12K$0.19$0.13$0.12
Refactor a module320K · 20K$0.33$0.23$0.21
Full-repo agent run900K · 45K$0.79$0.54$0.49

frequently asked

What is Qwen 3.6 Max Preview best for?
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 long-context reasoning, supporting a 262K token context window. The model includes an integrated thinking mode that preserves reasoning traces across multi-turn conversations and supports structured output and function calling. Access is available exclusively through the Alibaba Cloud Model Studio and Qwen Studio APIs; no open weights are provided.
How much does Qwen 3.6 Max Preview cost?
$1.30/M input and $7.80/M output, cache reads $0.26/M. In an agent loop most input is cache-read, so the effective input rate is about $0.57/M.
Which plan do I need?
Available on Go and above.
How do I switch to it?
Run cmd --model qwen/qwen3.6-max-preview, or type /model in a session and pick it. You can switch mid-session without losing context.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.1)commandcode.ai/models/qwen3-6-max-preview