Models / Alibaba / Qwen3.7 Max

Alibaba · qwen

Qwen3.7 Max

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

$2.50 in · $7.50 out

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

Provider input prices run from $0.83 to $3.00 per 1M tokens. Output prices run from $2.48 to $9.00.

Context
1,000,000
Max output
65,536
Cache read
$0.50
Cache write
$3.13
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
No
License
—
Released
May 21, 2026
Updated in source
May 21, 2026
Knowledge
—
Providers
31

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
Merge Gateway$0.83$2.48$0.17$1.03—
Cloudflare AI Gateway$1.25$3.75$0.25——
DevPass$1.25$3.75$0.25$3.13—
LLM Gateway$1.25$3.75$0.25——
Novita AI$1.25$3.75$0.25——
OrcaRouter$1.25$3.75$0.25$1.56—
Pioneer$1.25$3.75$0.25$1.56—
Kilo Gateway$1.48$4.43$0.30$1.84—
OpenRouter$1.48$4.43$0.30$1.84—
AIHubMix$1.69$5.07$0.17$2.11—
Ofox$1.71$5.14$0.17$2.14—
302.AI$1.80$5.30———
CrossModel$1.88$5.63$0.38$2.35—
Abacus$2.50$7.50———
Alibaba$2.50$7.50$0.50$3.13—
Alibabareference$2.50$7.50$0.50$3.13—
Charm Hyper$2.50$7.50$0.50——
ClinePass$2.50$7.50$0.50$3.13—
Deep Infra$2.50$7.50$0.50——
EmpirioLabs AI$2.50$7.50$2.50——
GMI Cloud$2.50$7.50$0.25$3.13—
Impossibl$2.50$7.50$0.50——
NanoGPT$2.50$7.50$0.50$3.13—
Requesty$2.50$7.50$0.25$3.13—
Vercel AI Gateway$2.50$7.50$0.50$3.13—
ZenMux$2.50$7.50$0.50$3.13—
Venice AI$2.70$8.05$0.27$3.35—
NEAR AI Cloud$2.80$7.50———
Modelis$3.00$9.00———
Alibaba Token Plan$0$0$0$0—
Alibaba Token Plan$0$0$0$0—

Jobs this model qualifies for

Comparisons