Skip to content

Step 3.7 Flash Thinking vs Gemma 4 31B Garnet

Gemma 4 31B Garnet is cheaper on output tokens, while Gemma 4 31B Garnet offers a larger context window. Choose Step 3.7 Flash Thinking or Gemma 4 31B Garnet based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecStep 3.7 Flash ThinkingGemma 4 31B Garnet
ProviderNanoGPTNanoGPT
Input / 1M tokens$0.20$0.31
Output / 1M tokens$1.15$0.31
Context window256K262K
Parameters
Open weightsNoNo
ReleasedMay 2026May 2026

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.