Is Phi-3.5-MoE-instruct or GPT-5.2 Codex cheaper?

Phi-3.5-MoE-instruct is cheaper on output tokens ($0.64 vs $14.00 per 1M).

Which has the larger context window, Phi-3.5-MoE-instruct or GPT-5.2 Codex?

GPT-5.2 Codex has the larger context window (400K tokens).

Phi-3.5-MoE-instruct vs GPT-5.2 Codex

Phi-3.5-MoE-instruct is cheaper on output tokens, while GPT-5.2 Codex offers a larger context window. Choose Phi-3.5-MoE-instruct or GPT-5.2 Codex based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Phi-3.5-MoE-instruct	GPT-5.2 Codex
Provider	Azure	Azure
Input / 1M tokens	$0.16	$1.75
Output / 1M tokens	$0.64	$14.00
Context window	128K	400K
Parameters	—	—
Open weights	Yes	No
Released	Aug 2024	Jan 2026

Phi-3.5-MoE-instruct details →GPT-5.2 Codex details →

FAQ

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