ModelPickr

Models / Alibaba / Qwen3.5 397B-A17B

Alibaba · qwen

Qwen3.5 397B-A17B

Large open Qwen multimodal MoE for visual agents and long technical tasks

$0.60 in · $3.60 out

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

Provider input prices run from $0.16 to $0.99 per 1M tokens. Output prices run from $0.99 to $4.96.

Context
262,144
Max output
65,536
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
—
Released
Feb 15, 2026
Updated in source
Feb 15, 2026
Knowledge
—
Providers
26

Hugging Face weights

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.

Estimated monthly cost

Qwen3.5 397B-A17B

$9.00

Cache hit is ignored because this model has no cache-read price.

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
AIHubMix$0.16$0.99———
Alibaba$0.17$1.03———
EmpirioLabs AI$0.17$1.03$0.17——
Merge Gateway$0.17$1.03$0.034——
OrcaRouter$0.17$1.03———
CrofAI$0.35$1.75$0.07——
Kilo Gateway$0.39$2.34———
SiliconFlow$0.39$2.34———
TokenGo$0.40$2.65$0.20——
Chutes$0.45$3.00$0.045——
NEAR AI Cloud$0.50$3.30$0.25——
OpenRouter$0.50$3.60$0.30——
NanoGPT$0.55$3.50$0.28——
Ofox$0.55$3.50$0.55——
Alibabareference$0.60$3.60———
Cloudflare AI Gateway$0.60$3.60———
DevPass$0.60$3.60———
Jalapeno Cloud$0.60$3.60———
LLMTR$0.60$3.60———
Novita AI$0.60$3.60———
Scaleway$0.60$3.60———
Cortecs$0.67$4.01———
Venice AI$0.75$4.50———
GreenPT$0.80$4.96———
Infomaniak$0.99$4.46——beta
UnoRouter$0$0———

Jobs this model qualifies for