Is GPT-3.5 Turbo Instruct or Phi-4 cheaper?

Phi-4 is cheaper on output tokens ($0.50 vs $2.00 per 1M).

Which has the larger context window, GPT-3.5 Turbo Instruct or Phi-4?

Phi-4 has the larger context window (128K tokens).

GPT-3.5 Turbo Instruct vs Phi-4

Phi-4 is cheaper on output tokens, while Phi-4 offers a larger context window. Choose GPT-3.5 Turbo Instruct or Phi-4 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-3.5 Turbo Instruct	Phi-4
Provider	Azure	Azure
Input / 1M tokens	$1.50	$0.13
Output / 1M tokens	$2.00	$0.50
Context window	4K	128K
Parameters	20B	—
Open weights	No	Yes
Released	Sep 2023	Dec 2024

GPT-3.5 Turbo Instruct details →Phi-4 details →

FAQ

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