Is Gemma 2 27B or Llama 3.3 Euryale 70B cheaper?

Gemma 2 27B is cheaper on output tokens ($0.89 vs $1.03 per 1M).

Which has the larger context window, Gemma 2 27B or Llama 3.3 Euryale 70B?

Llama 3.3 Euryale 70B has the larger context window (131K tokens).

Gemma 2 27B vs Llama 3.3 Euryale 70B

Gemma 2 27B is cheaper on output tokens, while Llama 3.3 Euryale 70B offers a larger context window. Choose Gemma 2 27B or Llama 3.3 Euryale 70B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Gemma 2 27B	Llama 3.3 Euryale 70B
Provider	AI/ML API	AI/ML API
Input / 1M tokens	$0.89	$0.89
Output / 1M tokens	$0.89	$1.03
Context window	8K	131K
Parameters	—	—
Open weights	Yes	Yes
Released	Jul 2024	Dec 2024

Gemma 2 27B details →Llama 3.3 Euryale 70B details →

FAQ

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