o3 vs o4-mini: token pricing & cost compared (July 2026)

How o3 (OpenAI) and o4-mini (OpenAI) actually compare on price — input, output, and total monthly cost at the MAU you care about. Updated against live OpenRouter pricing.

OpenAI

o3

Input: $2.00 / 1M tokens
Output: $8.00 / 1M tokens
Output / Input ratio: 4.0×
Context window: 200K

OpenAI

o4-mini

Input: $1.10 / 1M tokens
Output: $4.40 / 1M tokens
Output / Input ratio: 4.0×
Context window: 200K

The short answer

o4-mini is cheaper across the board for typical workloads.

Token pricing side-by-side

o3
o4-mini

Cost at your usage

Avg input tokens / call

Avg output tokens / call

Calls per active user / day: 5

Active days / month: 20

MAU: 1,000

Per call

$0.00500

Per user / mo

$0.5000

Total / mo

$500

o4-mini

Per call

$0.00275

Per user / mo

$0.2750

Total / mo

$275

o4-mini is cheaper by $0.2250/user/month — a saving of $225/month at 1,000 MAU.

Total monthly bill across MAU

o3
o4-mini

Same usage profile applied to both models; only the per-token price differs.

Run this against your real numbers

The mini-calculator above is a preview. Use the full tools to model power-user blast radius, gross margin, and 12-month spend forecasts.

Other comparisons

DeepSeek R1 vs o3 o1 vs o3 o4-mini vs Claude Sonnet 4.6 o3 vs Claude Opus 4.7 o3 vs GPT-5.1

Comparing o3 vs o4-mini on price alone never tells the whole story — output-token weighting, context length, and your usage profile change the answer dramatically. Use the calculators below for the full picture.