Is GPT-5-Codex or GPT-3.5 Turbo Instruct cheaper?

GPT-3.5 Turbo Instruct is cheaper on output tokens ($2.00 vs $10.00 per 1M).

Which has the larger context window, GPT-5-Codex or GPT-3.5 Turbo Instruct?

GPT-5-Codex has the larger context window (400K tokens).

GPT-5-Codex vs GPT-3.5 Turbo Instruct

GPT-3.5 Turbo Instruct is cheaper on output tokens, while GPT-5-Codex offers a larger context window. Choose GPT-5-Codex or GPT-3.5 Turbo Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-5-Codex	GPT-3.5 Turbo Instruct
Provider	Vercel AI Gateway	Vercel AI Gateway
Input / 1M tokens	$1.25	$1.50
Output / 1M tokens	$10.00	$2.00
Context window	400K	8K
Parameters	—	20B
Open weights	No	No
Released	Sep 2025	Sep 2023

GPT-5-Codex details →GPT-3.5 Turbo Instruct details →

FAQ

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