Qwen3.5 27B from Alibaba: $0.30 input and $2.40 output per 1M tokens, 262,144 context. Qwen vision-language model for visual reasoning, documents, and agent tasks Data last refreshed Oct 14, 2026, 05:43 PM UTC.

Models / Alibaba / Qwen3.5 27B

Alibaba · qwen

Qwen3.5 27B

Qwen vision-language model for visual reasoning, documents, and agent tasks

$0.30 in · $2.40 out

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

Provider input prices run from $0.085 to $0.30 per 1M tokens. Output prices run from $0.68 to $2.60.

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 23, 2026
Updated in source
Feb 23, 2026
Knowledge
—
Providers
17

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 27B

$5.40

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$0.085$0.68———
EmpirioLabs AI$0.086$0.69$0.086——
Merge Gateway$0.086$0.69$0.017——
OrcaRouter$0.086$0.69———
Kilo Gateway$0.20$1.56———
SiliconFlow$0.25$2.00———
Deep Infra$0.26$2.60———
OpenRouter$0.26$2.60———
Requesty$0.26$2.60———
Ofox$0.29$2.05$0.29——
Alibabareference$0.30$2.40———
DevPass$0.30$2.40———
Hugging Face$0.30$2.40———
Jalapeno Cloud$0.30$2.40———
LLM Gateway$0.30$2.40———
NanoGPT$0.30$2.40$0.15——
Novita AI$0.30$2.40———

Jobs this model qualifies for