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

GPT-3.5-Turbo is cheaper on output tokens ($1.40 vs $27.00 per 1M).

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

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

GPT-4-Turbo vs GPT-3.5-Turbo

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

Spec	GPT-4-Turbo	GPT-3.5-Turbo
Provider	Poe	Poe
Input / 1M tokens	$9.00	$0.45
Output / 1M tokens	$27.00	$1.40
Context window	128K	16K
Parameters	—	20B
Open weights	No	No
Released	Sep 2023	Sep 2023

GPT-4-Turbo 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.