token.app › Compare › Gemma 4 31B vs Inkling Small

Gemma 4 31B vs Inkling Small

Gemma 4 31B is 4.0× cheaper per token on a blended 3:1 basis. Inkling Small accepts the larger context window (524K).

Head to head
Blended price uses a 3:1 input:output mix
Gemma 4 31BInkling Small
ProviderGoogleThinkingmachines
Input $/1M$0.100$0.450
Output $/1M$0.340$1.20
Blended $/1M$0.160$0.637
Context window262K524K
Max output262K262K
ReleasedApr 2026Jul 2026
LicenceOpen weightsOpen weights
Choose Gemma 4 31B if…
  • Costs less per token — $0.160 vs $0.637 blended
Choose Inkling Small if…
  • Larger context window (524K)
  • Newer model (released Jul 2026)
FAQ
Which is better, Gemma 4 31B or Inkling Small?
We do not hold independently-run benchmark scores covering both Gemma 4 31B and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Gemma 4 31B cheaper than Inkling Small?
Gemma 4 31B is cheaper: $0.160 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.450. Output alone: $0.340 vs $1.20.
What context windows do Gemma 4 31B and Inkling Small have?
Gemma 4 31B: 262,144 tokens. Inkling Small: 524,288 tokens.
Who makes Gemma 4 31B and Inkling Small?
Gemma 4 31B is made by Google. Inkling Small is made by Thinkingmachines.
Related comparisons