Is Phi-3-medium-instruct (128k) or GPT-5 Mini cheaper?

Phi-3-medium-instruct (128k) is cheaper on output tokens ($0.68 vs $2.00 per 1M).

Which has the larger context window, Phi-3-medium-instruct (128k) or GPT-5 Mini?

GPT-5 Mini has the larger context window (272K tokens).

Phi-3-medium-instruct (128k) vs GPT-5 Mini

Phi-3-medium-instruct (128k) is cheaper on output tokens, while GPT-5 Mini offers a larger context window. Choose Phi-3-medium-instruct (128k) or GPT-5 Mini based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Phi-3-medium-instruct (128k)	GPT-5 Mini
Provider	Azure Cognitive Services	Azure Cognitive Services
Input / 1M tokens	$0.17	$0.25
Output / 1M tokens	$0.68	$2.00
Context window	128K	272K
Parameters	—	—
Open weights	Yes	No
Released	Apr 2024	Aug 2025

Phi-3-medium-instruct (128k) details →GPT-5 Mini details →

FAQ

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