Qwen 3.5 35B A3B pricing

API list price by Alibaba (Qwen) · checked Oct 23, 2026
Benchmarks and alternatives →
$0.25 / $2per 1M tokens in / out
#157on OpenRouter by tokens · 21.5B / week

Price sheetper 1M tokens

Input$0.25list
Output$2
Context · max output262K · 66Ktokens

Where to buy11 providers · per 1M tokens

ProviderInputOutputContext
lab-qwen$0.057$0.46—
model-studio-international$0.057$0.46—
Darkbloom$0.065$0.75262K
DeepInfra$0.14$1262K
Parasail$0.15$1262K
Venice$0.15$1256K
Alibaba$0.16$1.30262K
AtlasCloud$0.23$1.80262K
SiliconFlow$0.24$1.80262K
Novita$0.25$2—
qwen$0.25$2—

In Alibaba (Qwen)'s line-upper 1M in / out

Qwen Max$0.34 / $1.38−12%
Qwen3 Coder 480B A35B$0.22 / $1.80−11%
Qwen 3.6 Plus 2026-04-02$0.28 / $1.65−10%
Qwen 3.5 35B A3B$0.25 / $2this model
Qwen VL OCR 2024-10-28$0.72 / $0.72+4%
Qwen Plus Character Ja$0.50 / $1.40+5%
Qwen 3 Omni Flash$0.43 / $1.66+7%
<

Cheaper for the same workvs Qwen 3.5 35B A3B

MiMo v2.6 Pro thinkingOpen-21%score ×2.4$0.13
DeepSeek V4.1 Flash 1017 maxOpen-24%score ×2.3$0.26
Claude Haiku 5.5 max-71%score ×2.2$0.21
MiniMax M3.1 Flash thinking-62%score ×2.2$0.22
GLM 5.3 Flash maxOpen-65%score ×2.2$0.28

Pricing questions

How much does Qwen 3.5 35B A3B cost?›

$0.25 per 1M input tokens and $2 per 1M output tokens.

Is Qwen 3.5 35B A3B free to use?›

There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.

Is Qwen 3.5 35B A3B cheaper than Qwen3 VL 30B A3B Instruct?›

No: $0.25 / $2 against $0.15 / $0.50, 189% more per token.

What is a cheaper alternative to Qwen 3.5 35B A3B?›

MiMo v2.6 Pro at thinking effort costs -21% per task with a score ×2.4 on Humanity's Last Exam.