Qwen3.5 397B A17B vs Qwen3.6 35B A3B

Price, context window & benchmark comparison

Q

Qwen3.5 397B A17B

Qwen (Alibaba)
$0.55 / $3.50
Input / Output · per 1M tokens
VS
Q

Qwen3.6 35B A3B

Qwen (Alibaba)
$0.15 / $1.00
Input / Output · per 1M tokens
Compare different models
Q
Q
Verdict: Qwen3.6 35B A3B is 3.6× cheaper than Qwen3.5 397B A17B on a typical 3:1 input/output mix. Qwen3.5 397B A17B scores higher on the Artificial Analysis Intelligence Index (18.4 vs 18.2).
Qwen3.5 397B A17BQwen3.6 35B A3B
Input price / 1M$0.55$0.15
Output price / 1M$3.50$1.00
Blended price (3:1)$1.29$0.36
Cached input / 1M$0.23$0.05
Context window262K262K
Max output236K236K
Intelligence index18.418.2
Coding index48.241.9
Providers
Best provider uptime (30m)
Vision inputYesYes
ReasoningYesYes
Tool callingYesYes
Released2026-02-162026-04-27
Retirement

Cost calculator

FAQ

Which is cheaper, Qwen3.5 397B A17B or Qwen3.6 35B A3B?

Qwen3.6 35B A3B is 3.6× cheaper than Qwen3.5 397B A17B on a typical 3:1 input/output mix.

Qwen3.5 397B A17B vs Qwen3.6 35B A3B: which has a bigger context window?

Qwen3.5 397B A17B: 262,144 tokens. Qwen3.6 35B A3B: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Qwen3.5 397B A17B ≈ $2,850, Qwen3.6 35B A3B ≈ $800.00.

More comparisons