Is GPT-3.5 Turbo 16k or GPT-5.3 Codex cheaper?

GPT-3.5 Turbo 16k is cheaper on output tokens ($4.00 vs $14.00 per 1M).

Which has the larger context window, GPT-3.5 Turbo 16k or GPT-5.3 Codex?

GPT-5.3 Codex has the larger context window (400K tokens).

GPT-3.5 Turbo 16k vs GPT-5.3 Codex

GPT-3.5 Turbo 16k is cheaper on output tokens, while GPT-5.3 Codex offers a larger context window. Choose GPT-3.5 Turbo 16k or GPT-5.3 Codex based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-3.5 Turbo 16k	GPT-5.3 Codex
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$3.00	$1.75
Output / 1M tokens	$4.00	$14.00
Context window	16K	400K
Parameters	—	—
Open weights	No	No
Released	Aug 2023	Feb 2026

GPT-3.5 Turbo 16k details →GPT-5.3 Codex details →

FAQ

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