Is Phi-3-small-instruct (8k) or GPT-5.2 cheaper?

Phi-3-small-instruct (8k) is cheaper on output tokens ($0.60 vs $14.00 per 1M).

Which has the larger context window, Phi-3-small-instruct (8k) or GPT-5.2?

GPT-5.2 has the larger context window (400K tokens).

Phi-3-small-instruct (8k) vs GPT-5.2

Phi-3-small-instruct (8k) is cheaper on output tokens, while GPT-5.2 offers a larger context window. Choose Phi-3-small-instruct (8k) or GPT-5.2 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Phi-3-small-instruct (8k)	GPT-5.2
Provider	Azure Cognitive Services	Azure Cognitive Services
Input / 1M tokens	$0.15	$1.75
Output / 1M tokens	$0.60	$14.00
Context window	8K	400K
Parameters	—	—
Open weights	Yes	No
Released	Apr 2024	Dec 2025

Phi-3-small-instruct (8k) details →GPT-5.2 details →

FAQ

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