Is GPT-OSS 20B or Llama 3.3 70B Instruct cheaper?

GPT-OSS 20B is cheaper on output tokens ($0.14 vs $0.38 per 1M).

Which has the larger context window, GPT-OSS 20B or Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct has the larger context window (128K tokens).

GPT-OSS 20B vs Llama 3.3 70B Instruct

GPT-OSS 20B is cheaper on output tokens, while Llama 3.3 70B Instruct offers a larger context window. Choose GPT-OSS 20B or Llama 3.3 70B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-OSS 20B	Llama 3.3 70B Instruct
Provider	IO.NET	IO.NET
Input / 1M tokens	$0.03	$0.13
Output / 1M tokens	$0.14	$0.38
Context window	64K	128K
Parameters	21B	—
Open weights	Yes	Yes
Released	Dec 2024	Dec 2024

GPT-OSS 20B details →Llama 3.3 70B Instruct details →

FAQ

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