Is Llama 3.2 90B Vision Instruct or DeepSeek R1 cheaper?

Llama 3.2 90B Vision Instruct is cheaper on output tokens ($0.40 vs $8.75 per 1M).

Which has the larger context window, Llama 3.2 90B Vision Instruct or DeepSeek R1?

DeepSeek R1 has the larger context window (128K tokens).

Llama 3.2 90B Vision Instruct vs DeepSeek R1

Llama 3.2 90B Vision Instruct is cheaper on output tokens, while DeepSeek R1 offers a larger context window. Choose Llama 3.2 90B Vision Instruct or DeepSeek R1 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama 3.2 90B Vision Instruct	DeepSeek R1
Provider	IO.NET	IO.NET
Input / 1M tokens	$0.35	$2.00
Output / 1M tokens	$0.40	$8.75
Context window	16K	128K
Parameters	—	671B
Open weights	Yes	Yes
Released	Sep 2024	Jan 2025

Llama 3.2 90B Vision Instruct details →DeepSeek R1 details →

FAQ

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