MiMo-V2.6-Pro-UltraSpeed vs Qwen3.5 397B A17B

Price, context window & benchmark comparison

MiMo-V2.6-Pro-UltraSpeed

Xiaomi

$4.35 / $8.70

Input / Output · per 1M tokens

Qwen3.5 397B A17B

Qwen (Alibaba)

$0.55 / $3.50

Input / Output · per 1M tokens

Compare different models

Verdict: Qwen3.5 397B A17B is 4.2× cheaper than MiMo-V2.6-Pro-UltraSpeed on a typical 3:1 input/output mix. MiMo-V2.6-Pro-UltraSpeed has the larger context window (1M vs 262K).

	MiMo-V2.6-Pro-UltraSpeed	Qwen3.5 397B A17B
Input price / 1M	$4.35	$0.55
Output price / 1M	$8.70	$3.50
Blended price (3:1)	$5.44	$1.29
Cached input / 1M	$0.036	$0.23
Context window	1M	262K
Max output	131K	236K
Intelligence index	—	18.4
Coding index	—	48.2
Providers	1	—
Best provider uptime (30m)	100.0%	—
Vision input	Yes	Yes
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Released	2026-09-21	2026-02-16
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, MiMo-V2.6-Pro-UltraSpeed or Qwen3.5 397B A17B?

Qwen3.5 397B A17B is 4.2× cheaper than MiMo-V2.6-Pro-UltraSpeed on a typical 3:1 input/output mix.

MiMo-V2.6-Pro-UltraSpeed vs Qwen3.5 397B A17B: which has a bigger context window?

MiMo-V2.6-Pro-UltraSpeed: 1,048,576 tokens. Qwen3.5 397B A17B: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: MiMo-V2.6-Pro-UltraSpeed ≈ $13,050, Qwen3.5 397B A17B ≈ $2,850.

More comparisons