Is Gemma 4 31B IT or openai/gpt-oss-20b cheaper?

openai/gpt-oss-20b is cheaper on output tokens ($0.18 vs $0.40 per 1M).

Which has the larger context window, Gemma 4 31B IT or openai/gpt-oss-20b?

Gemma 4 31B IT has the larger context window (262K tokens).

Gemma 4 31B IT vs openai/gpt-oss-20b

openai/gpt-oss-20b is cheaper on output tokens, while Gemma 4 31B IT offers a larger context window. Choose Gemma 4 31B IT or openai/gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Gemma 4 31B IT	openai/gpt-oss-20b
Provider	SiliconFlow	SiliconFlow
Input / 1M tokens	$0.13	$0.04
Output / 1M tokens	$0.40	$0.18
Context window	262K	131K
Parameters	—	21B
Open weights	No	No
Released	Apr 2026	Aug 2025

Gemma 4 31B IT details →openai/gpt-oss-20b details →

FAQ

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