Head to head

o3 vs GPT-4.1

o3: legacyGPT-4.1: legacyheavy tier

Verdict · modelled basis

o3 costs 2.6x less per solved task.

On output token price alone, GPT-4.1 looks 1.0x cheaper (1.0x on input). The ranking reverses once you divide by pass rate — the cheaper tokens do not win the task.

Source: Aider polyglot benchmark · verified 2026-08-21 · prices from each provider's pricing page

Input $/M tokens

lower is better

o3$2
GPT-4.1$2

Output $/M tokens

lower is better

o3$8
GPT-4.1$8

Cost per solved task

modelled basis · lower is better

o3$1.99
GPT-4.1$5.15

	o3	GPT-4.1
Input $/Mtok	$2	$2
Output $/Mtok	$8	$8
Cached input $/Mtok	$0.5	$0.5
Pass rate	81%	52%
Pass rate source	Aider	Aider
Cost basis	modelled	modelled
Cost per solved task	$1.99	$5.15

verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· o3· GPT-4.1