Mistral Small 4 vs Qwen3.5-122B-A10B

Price, context window & benchmark comparison

M

Mistral Small 4

Mistral AI
$0.15 / $0.60
Input / Output · per 1M tokens
VS
Q

Qwen3.5-122B-A10B

Qwen (Alibaba)
$0.26 / $2.08
Input / Output · per 1M tokens
Compare different models
M
Q
Verdict: Mistral Small 4 is 2.7× cheaper than Qwen3.5-122B-A10B on a typical 3:1 input/output mix. Qwen3.5-122B-A10B scores higher on the Artificial Analysis Intelligence Index (15.6 vs 11.3).
Mistral Small 4Qwen3.5-122B-A10B
Input price / 1M$0.15$0.26
Output price / 1M$0.60$2.08
Blended price (3:1)$0.26$0.72
Cached input / 1M$0.015
Context window262K262K
Max output210K66K
Intelligence index11.315.6
Coding index26.645.7
Providers3
Best provider uptime (30m)100.0%
Vision inputYesYes
ReasoningYesYes
Tool callingYesYes
Released2026-03-162026-02-25
Retirement

Cost calculator

FAQ

Which is cheaper, Mistral Small 4 or Qwen3.5-122B-A10B?

Mistral Small 4 is 2.7× cheaper than Qwen3.5-122B-A10B on a typical 3:1 input/output mix.

Mistral Small 4 vs Qwen3.5-122B-A10B: which has a bigger context window?

Mistral Small 4: 262,144 tokens. Qwen3.5-122B-A10B: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Mistral Small 4 ≈ $600.00, Qwen3.5-122B-A10B ≈ $1,560.

More comparisons