Is GPT-5.4 nano or GPT-3.5-turbo cheaper?

GPT-5.4 nano is cheaper on output tokens ($1.25 vs $1.50 per 1M).

Which has the larger context window, GPT-5.4 nano or GPT-3.5-turbo?

GPT-5.4 nano has the larger context window (400K tokens).

GPT-5.4 nano vs GPT-3.5-turbo

GPT-5.4 nano is cheaper on output tokens, while GPT-5.4 nano offers a larger context window. Choose GPT-5.4 nano or GPT-3.5-turbo based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-5.4 nano	GPT-3.5-turbo
Provider	OrcaRouter	OrcaRouter
Input / 1M tokens	$0.20	$0.50
Output / 1M tokens	$1.25	$1.50
Context window	400K	16K
Parameters	—	20B
Open weights	No	No
Released	Mar 2026	Mar 2023

GPT-5.4 nano details →GPT-3.5-turbo details →

FAQ

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