Gemma 3 12B vs Qwen3 235B A22B Thinking 2507

Price, context window & benchmark comparison

G

Gemma 3 12B

Google
$0.05 / $0.15
Input / Output · per 1M tokens
VS
Q

Qwen3 235B A22B Thinking 2507

Qwen (Alibaba)
$0.23 / $2.30
Input / Output · per 1M tokens
Compare different models
G
Q
Verdict: Gemma 3 12B is 10.0× cheaper than Qwen3 235B A22B Thinking 2507 on a typical 3:1 input/output mix. Qwen3 235B A22B Thinking 2507 scores higher on the Artificial Analysis Intelligence Index (12.7 vs 3.8).
Gemma 3 12BQwen3 235B A22B Thinking 2507
Input price / 1M$0.05$0.23
Output price / 1M$0.15$2.30
Blended price (3:1)$0.075$0.75
Cached input / 1M
Context window131K131K
Max output16K118K
Intelligence index3.812.7
Coding index5.822.1
Providers
Best provider uptime (30m)
Vision inputYesNo
ReasoningNoYes
Tool callingYesYes
Released2025-03-132025-07-25
Retirement

Cost calculator

FAQ

Which is cheaper, Gemma 3 12B or Qwen3 235B A22B Thinking 2507?

Gemma 3 12B is 10.0× cheaper than Qwen3 235B A22B Thinking 2507 on a typical 3:1 input/output mix.

Gemma 3 12B vs Qwen3 235B A22B Thinking 2507: which has a bigger context window?

Gemma 3 12B: 131,072 tokens. Qwen3 235B A22B Thinking 2507: 131,072 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemma 3 12B ≈ $175.00, Qwen3 235B A22B Thinking 2507 ≈ $1,610.

More comparisons