Is Llama 3.1 8B Instruct FP8 or GPT OSS 20B cheaper?

Llama 3.1 8B Instruct FP8 is cheaper on output tokens ($0.29 vs $0.30 per 1M).

Which has the larger context window, Llama 3.1 8B Instruct FP8 or GPT OSS 20B?

Both models offer a similar context window.

Llama 3.1 8B Instruct FP8 vs GPT OSS 20B

Llama 3.1 8B Instruct FP8 is cheaper on output tokens. Choose Llama 3.1 8B Instruct FP8 or GPT OSS 20B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama 3.1 8B Instruct FP8	GPT OSS 20B
Provider	Cloudflare AI Gateway	Cloudflare AI Gateway
Input / 1M tokens	$0.15	$0.20
Output / 1M tokens	$0.29	$0.30
Context window	128K	128K
Parameters	—	21B
Open weights	No	No
Released	Apr 2025	Aug 2025

Llama 3.1 8B Instruct FP8 details →GPT OSS 20B details →

FAQ

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