Models / Alibaba / Qwen3.6 35B-A3B

Alibaba · qwen

Qwen3.6 35B-A3B

Open multimodal Qwen MoE for local agents that need vision, audio, and code

$0.25 in · $1.49 out

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

Provider input prices run from $0.045 to $5.00 per 1M tokens. Output prices run from $0.30 to $10.00.

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
Apr 17, 2026
Updated in source
Apr 17, 2026
Knowledge
—
Providers
36

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

Qwen3.6 35B-A3B

$3.72

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
engy$0.045$0.30$0.015——
EmpirioLabs AI$0.07$0.42$0.035——
SaladCloud AI Gateway$0.09$0.60———
Kilo Gateway$0.10$0.95$0.10——
OpenRouter$0.10$0.95$0.10——
Venice AI$0.10$1.00———
Pioneer$0.14$1.00$0.028$0.18—
AKI.IO$0.15$0.50———
Ambient$0.15$1.00$0.15$0—
Hugging Face$0.15$0.95———
Umans AI$0.15$1.00$0.05——
Cortecs$0.17$0.56———
NEAR AI Cloud$0.17$1.10$0.056——
Zenifra$0.19$0.48———
NanoGPT$0.20$1.27$0.10——
SiliconFlow$0.20$1.60———
Alibabareference$0.25$1.49———
DevPass$0.25$1.49———
LLM Gateway$0.25$1.49———
Merge Gateway$0.25$1.49$0.05——
Novita AI$0.25$1.49———
Opper$0.25$1.49———
OrcaRouter$0.25$1.49———
CoreWeave$0.25$1.25$0.25——
Scaleway$0.25$1.50——beta
AIHubMix$0.25$1.52———
302.AI$0.28$1.71———
Neuralwatt$0.29$1.15$0.029——
GreenPT$0.34$2.05———
evroc$0.35$1.38———
LLMTR$5.00$10.00———
Hetzner$0$0$0—beta
InferX$0$0———
NaN$0$0———
QVAC$0$0———
Umans AI Coding Plan$0$0$0$0—

Jobs this model qualifies for

Comparisons