Is Gemma 4 31B Instruct or Llama 3.3 70B cheaper?

Llama 3.3 70B is cheaper on output tokens ($0.88 vs $0.97 per 1M).

Which has the larger context window, Gemma 4 31B Instruct or Llama 3.3 70B?

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

Gemma 4 31B Instruct vs Llama 3.3 70B

Llama 3.3 70B is cheaper on output tokens, while Gemma 4 31B Instruct offers a larger context window. Choose Gemma 4 31B Instruct or Llama 3.3 70B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Gemma 4 31B Instruct	Llama 3.3 70B
Provider	Together AI	Together AI
Input / 1M tokens	$0.39	$0.88
Output / 1M tokens	$0.97	$0.88
Context window	262K	131K
Parameters	—	70B
Open weights	Yes	Yes
Released	Apr 2026	Dec 2024

Gemma 4 31B Instruct details →Llama 3.3 70B details →

FAQ

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