Is Phi-3-medium-instruct (128k) or DeepSeek-R1 cheaper?

Phi-3-medium-instruct (128k) is cheaper on output tokens ($0.68 vs $5.40 per 1M).

Which has the larger context window, Phi-3-medium-instruct (128k) or DeepSeek-R1?

DeepSeek-R1 has the larger context window (164K tokens).

Phi-3-medium-instruct (128k) vs DeepSeek-R1

Phi-3-medium-instruct (128k) is cheaper on output tokens, while DeepSeek-R1 offers a larger context window. Choose Phi-3-medium-instruct (128k) or DeepSeek-R1 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Phi-3-medium-instruct (128k)	DeepSeek-R1
Provider	Azure	Azure
Input / 1M tokens	$0.17	$1.35
Output / 1M tokens	$0.68	$5.40
Context window	128K	164K
Parameters	—	671B
Open weights	Yes	Yes
Released	Apr 2024	Jan 2025

Phi-3-medium-instruct (128k) details →DeepSeek-R1 details →

FAQ

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