Qwen3.5 397B-A17B pricing & specs

Alibaba (Qwen) · released 2026-02-15 · ● verified 2026-10-11

input / 1M$0.60
output / 1M$3.60
context262.1K
max output65.5K

// price history ($/1M tokens)

$4.14
input $/1Moutput $/1M2026-02-17 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs Qwen3.5 397B-A17B
Gemma 4 E2B IT$0.04$0.08131.1K−96.3%
Gemini 2.5 Flash-Lite$0.10$0.401.05M−87%
Qwen3.8 Omni Flash$0.15$0.471M−83%
Qwen3.6 35B-A3B$0.248$1.485262.1K−58.7%
Gemini 3.1 Flash Lite$0.25$1.501.05M−58.3%

// price by host

hostin $/1Mout $/1M
Novita AI$0.60$3.60
Scaleway$0.60$3.60

// faq

How much does Qwen3.5 397B-A17B cost?

Qwen3.5 397B-A17B costs $0.60 per million input tokens and $3.60 per million output tokens. At 50M input and 10M output tokens per month that is about $66.00.

What is the context window of Qwen3.5 397B-A17B?

262.1K tokens, with up to 65.5K output tokens per request.

What are cheaper alternatives to Qwen3.5 397B-A17B?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Gemini 2.5 Flash-Lite ($0.10 in / $0.40 out), Qwen3.8 Omni Flash ($0.15 in / $0.47 out) offer the same input types and capabilities for less.

Is Qwen3.5 397B-A17B open weights?

Yes. It is available from 2 tracked hosts; the cheapest is Novita AI at $0.60 input and $3.60 output per million tokens.

// spec sheet

input / 1M
$0.60
output / 1M
$3.60
blended (3:1)
$1.35
context
262.1K
max output
65.5K
input types
text · image · video · audio
reasoning
yes
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
n/a
price source
Alibaba (Qwen)

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Gemini 2.5 Flash-Lite$0.10$0.40$9.00
Qwen3.8 Omni Flash$0.15$0.47$12.20
Qwen3.5 397B-A17B$0.60$3.60$66.00

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.