ModelPickr

Models / Alibaba / Qwen3.5 35B-A3B

Alibaba · qwen

Qwen3.5 35B-A3B

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

$0.25 in · $2.00 out

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

Provider input prices run from $0.056 to $0.29 per 1M tokens. Output prices run from $0.45 to $2.00.

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
18

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 35B-A3B

$4.50

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$0.056$0.45———
EmpirioLabs AI$0.057$0.46$0.057——
Merge Gateway$0.057$0.46$0.02——
OrcaRouter$0.057$0.46———
302.AI$0.06$0.46———
Requesty$0.14$1.00$0.05——
OpenRouter$0.15$1.00$0.05——
Venice AI$0.15$1.00$0.05——
Kilo Gateway$0.16$1.30———
NanoGPT$0.23$1.80$0.11——
SiliconFlow$0.24$1.80———
Alibabareference$0.25$2.00———
DevPass$0.25$2.00———
Hugging Face$0.25$2.00———
Jalapeno Cloud$0.25$2.00———
LLM Gateway$0.25$2.00———
Novita AI$0.25$2.00———
Ofox$0.29$1.83$0.29——

Jobs this model qualifies for