Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Llama 3.2 3B Instruct (Deep Infra) vs Gemma 3 4B

Llama 3.2 3B Instruct (Deep Infra) is cheaper on output tokens. Choose Llama 3.2 3B Instruct (Deep Infra) or Gemma 3 4B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecLlama 3.2 3B Instruct (Deep Infra)Gemma 3 4B
ProviderEden AIGoogle
Input / 1M tokens$0.02$0.04
Output / 1M tokens$0.02$0.05
Context window131K131K
Parameters——
Open weightsYes—
ReleasedSep 2024—
Epoch Capabilities Index score—116
Llama 3.2 3B Instruct (Deep Infra) details →Gemma 3 4B details →

FAQ

Is Llama 3.2 3B Instruct (Deep Infra) or Gemma 3 4B cheaper?

Llama 3.2 3B Instruct (Deep Infra) is cheaper on output tokens ($0.02 vs $0.05 per 1M).

Which has the larger context window, Llama 3.2 3B Instruct (Deep Infra) or Gemma 3 4B?

Both models offer a similar context window.

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