Qwen 4 Max

qwen/qwen4-max

flagship coding, agentic & knowledge work.

cmd --model qwen/qwen4-max
Intelligence index
not yet scored
Coding index
not yet scored
Input
$1.50 /M
Output
$4.50 /M
Cache read
$0.07 /M
Agent-loop cost
$0.50 /M in
Context window
1M tokens
Released
November 15, 2026
Modalities
→

vs. the lineup

Qwen 4 Max beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingInput $/MOutput $/MBlended $/MContext
Qwen 3.8 Max 090245.4◆76.2◆$2$6$31M◆
Qwen 3.8 Max40.271.8$2$6$31M◆
Qwen 3.8 27B33.768.1$0.40$3$1.05262K
Qwen 4 Max ◆——$1.50$4.50$2.251M◆
Qwen 3.8 Omni Flash——$0.15◆$0.47◆$0.23◆1M◆
Qwen 3.8 Max Prime——$4$12$61M◆
DeepSeek V4 Pro (latest)pinned3668.8$0.66$1.98$0.991M◆
DeepSeek V4 Flash (latest)pinned3469.1$0.15◆$0.60$0.261M◆

usage calculator

How far a month of credits goes on Qwen 4 Max.

Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.0058 · in $1.50 · out $4.50 · cache $0.07 per M
fresh input 21%output 14%cache reads 65%
Requests / 30 days
1.0K
$6 credits ÷ $0.0058 per request
~208 quick fixes~42 bug fixes~7 feature PRs

what real work costs

Real coding tasks priced end to end on Qwen 4 Max, from a quick lookup to a full-repo agent run.

One agent task
$0.13
180K in at 75% cache hit, 12K out
What you pay
$0.69 /M
all-in across every token that task touched
Sticker input
$1.50 /M
cache reads bill at $0.07 /M instead
TaskTokens in · outQwen 4 MaxMuse Spark 1.3Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.0062$0.0063$0.0065
Review a 500-line PR60K · 4K$0.05$0.05$0.04
Fix a bug (agent loop)180K · 12K$0.13$0.13$0.12
Refactor a module320K · 20K$0.24$0.23$0.21
Full-repo agent run900K · 45K$0.55$0.54$0.49

frequently asked

How much does Qwen 4 Max cost?
$1.50/M input and $4.50/M output, cache reads $0.07/M. In an agent loop most input is cache-read, so the effective input rate is about $0.50/M.
Which plan do I need?
Available on Go and above.
How do I switch to it?
Run cmd --model qwen/qwen4-max, 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 (v4.3)commandcode.ai/models/qwen4-max