ModelPickr

Models / Alibaba / Qwen3.6 Max Preview

Alibaba · qwen

Qwen3.6 Max Preview

Flagship Qwen model for complex reasoning, coding, and agentic workflows

$1.30 in · $7.80 out

per 1M tokens · first-party price. Reference price from Alibaba, the lab's own listing.

Provider input prices run from $0.65 to $2.15 per 1M tokens. Output prices run from $3.90 to $12.86.

Context
262,144
Max output
65,536
Cache read
$0.13
Cache write
$1.63
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
No
License
—
Released
Apr 20, 2026
Updated in source
Apr 20, 2026
Knowledge
2025-04
Providers
7

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
AI/ML API$0.65$3.90———
NanoGPT$1.04$6.24$0.52——
Pioneer$1.04$6.24$0.21$1.30—
Alibabareference$1.30$7.80$0.13$1.63—
Merge Gateway$1.31$7.88———
Alibaba$1.32$7.90$0.13——
Ofox$2.15$12.86$0.20$1.17—

Jobs this model qualifies for