Qwen 3.8 Max Prime
qwen/qwen3.8-max-prime
high-speed Qwen 3.8 Max: 1.5–2× faster output.
cmd --model qwen/qwen3.8-max-prime
Intelligence index
not yet scored
Coding index
not yet scored
Input
$4 /M
Output
$12 /M
Cache read
$0.50 /M
Agent-loop cost
$1.55 /M in
Context window
1M tokens
Released
September 23, 2026
Modalities
→
vs. the lineup
Qwen 3.8 Max Prime beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
pin a rival:
| Model | Intelligence | Coding | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|
| Qwen 3.8 Max 0902 | 45.4◆ | 76.2◆ | $2◆ | $6◆ | $3◆ | 1M◆ |
| Qwen 3.8 Max | 40.2◆ | 71.8◆ | $2◆ | $6◆ | $3◆ | 1M◆ |
| Qwen 3.8 27B | 33.7◆ | 68.1◆ | $0.40◆ | $3◆ | $1.05◆ | 262K◆ |
| Qwen 3.8 Max Prime ◆ | —◆ | —◆ | $4◆ | $12◆ | $6◆ | 1M◆ |
| Qwen 3.8 Omni Flash | —◆ | —◆ | $0.15◆ | $0.47◆ | $0.23◆ | 1M◆ |
| Qwen 3.8 Flash | —◆ | —◆ | $0.16◆ | $0.47◆ | $0.24◆ | 1M◆ |
| DeepSeek V4 Pro (latest)pinned | 36◆ | 68.8◆ | $0.66◆ | $1.98◆ | $0.99◆ | 1M◆ |
| DeepSeek V4 Flash (latest)pinned | 34◆ | 69.1◆ | $0.15◆ | $0.60◆ | $0.26◆ | 1M◆ |
usage calculator
How far a month of credits goes on Qwen 3.8 Max Prime.
Qwen 3.8 Max Prime runs on GOAT and up — from $10/mo.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.030 · in $4 · out $12 · cache $0.50 per M
fresh input 11%output 7%cache reads 82%
Requests / 30 days
659
$20 credits ÷ $0.030 per request
~132 quick fixes~26 bug fixes~4 feature PRs
what real work costs
Real coding tasks priced end to end on Qwen 3.8 Max Prime, from a quick lookup to a full-repo agent run.
One agent task
$0.39
180K in at 75% cache hit, 12K out
What you pay
$2.04 /M
all-in across every token that task touched
Sticker input
$4 /M
cache reads bill at $0.50 /M instead
| Task | Tokens in · out | Qwen 3.8 Max Prime | Claude Sonnet 5.5 | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.02 | $0.01 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.14 | $0.08 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.39 | $0.22 | $0.12 |
| Refactor a module | 320K · 20K | $0.71 | $0.40 | $0.21 |
| Full-repo agent run | 900K · 45K | $1.68 | $0.92 | $0.49 |
frequently asked
How much does Qwen 3.8 Max Prime cost?
$4/M input and $12/M output, cache reads $0.50/M. In an agent loop most input is cache-read, so the effective input rate is about $1.55/M.Which plan do I need?
Available on GOAT and above.
How do I switch to it?
Run
cmd --model qwen/qwen3.8-max-prime, 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/qwen3-8-max-prime