Is Gemma 4 31B Split-Untied or Llama-xLAM-2 70B fc-r cheaper?

Gemma 4 31B Split-Untied is cheaper on output tokens ($0.30 vs $2.50 per 1M).

Which has the larger context window, Gemma 4 31B Split-Untied or Llama-xLAM-2 70B fc-r?

Gemma 4 31B Split-Untied has the larger context window (262K tokens).

Gemma 4 31B Split-Untied vs Llama-xLAM-2 70B fc-r

Gemma 4 31B Split-Untied is cheaper on output tokens, while Gemma 4 31B Split-Untied offers a larger context window. Choose Gemma 4 31B Split-Untied or Llama-xLAM-2 70B fc-r based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Gemma 4 31B Split-Untied	Llama-xLAM-2 70B fc-r
Provider	NanoGPT	NanoGPT
Input / 1M tokens	$0.10	$2.50
Output / 1M tokens	$0.30	$2.50
Context window	262K	128K
Parameters	—	—
Open weights	Yes	Yes
Released	Sep 2026	Apr 2025

Gemma 4 31B Split-Untied details →Llama-xLAM-2 70B fc-r details →

FAQ

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