Is GLM-5.2 or Gemma 4 31B Instruct cheaper?

Gemma 4 31B Instruct is cheaper on output tokens ($0.55 vs $4.84 per 1M).

Which has the larger context window, GLM-5.2 or Gemma 4 31B Instruct?

GLM-5.2 has the larger context window (524K tokens).

GLM-5.2 vs Gemma 4 31B Instruct

Gemma 4 31B Instruct is cheaper on output tokens, while GLM-5.2 offers a larger context window. Choose GLM-5.2 or Gemma 4 31B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GLM-5.2	Gemma 4 31B Instruct
Provider	Berget.AI	Berget.AI
Input / 1M tokens	$1.54	$0.28
Output / 1M tokens	$4.84	$0.55
Context window	524K	128K
Parameters	—	—
Open weights	Yes	Yes
Released	Jun 2026	Apr 2026

GLM-5.2 details →Gemma 4 31B Instruct details →

FAQ

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