Gemma 4 31B vs Inkling Small

Price, context window & benchmark comparison

Google

Gemma 4 31B

Google
$0.20 / $0.40
Input / Output · per 1M tokens
VS
Thinkingmachines

Inkling Small

Thinkingmachines
$0.45 / $1.20
Input / Output · per 1M tokens
Compare different models
Google
Thinkingmachines
Verdict: Gemma 4 31B is 2.5× cheaper than Inkling Small on a typical 3:1 input/output mix. Inkling Small scores higher on the Artificial Analysis Intelligence Index (12.9 vs 4.4). Inkling Small has the larger context window (524K vs 262K).
Gemma 4 31BInkling Small
Input price / 1M$0.20$0.45
Output price / 1M$0.40$1.20
Blended price (3:1)$0.25$0.64
Cached input / 1M—$0.10
Context window262K524K
Max output16K262K
Intelligence index4.412.9
Coding index43.452.9
Providers——
Best provider uptime (30m)——
Vision inputYesYes
ReasoningYesYes
Tool callingYesYes
Released2026-04-022026-07-30
Retirement——

Cost calculator

FAQ

Which is cheaper, Gemma 4 31B or Inkling Small?

Gemma 4 31B is 2.5× cheaper than Inkling Small on a typical 3:1 input/output mix.

Gemma 4 31B vs Inkling Small: which has a bigger context window?

Gemma 4 31B: 262,144 tokens. Inkling Small: 524,288 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemma 4 31B ≈ $600.00, Inkling Small ≈ $1,500.

More comparisons