Is Phi-3.5-mini-instruct or GPT-4o mini cheaper?

Phi-3.5-mini-instruct is cheaper on output tokens ($0.52 vs $0.60 per 1M).

Which has the larger context window, Phi-3.5-mini-instruct or GPT-4o mini?

Both models offer a similar context window.

Phi-3.5-mini-instruct vs GPT-4o mini

Phi-3.5-mini-instruct is cheaper on output tokens. Choose Phi-3.5-mini-instruct or GPT-4o mini based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Phi-3.5-mini-instruct	GPT-4o mini
Provider	Azure Cognitive Services	Azure Cognitive Services
Input / 1M tokens	$0.13	$0.15
Output / 1M tokens	$0.52	$0.60
Context window	128K	128K
Parameters	—	—
Open weights	Yes	No
Released	Aug 2024	Jul 2024

Phi-3.5-mini-instruct details →GPT-4o mini details →

FAQ

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