Home/Models/o4-mini

o4-mini

by OpenAI· Released 2025-04
Official Docs ↗

o4-mini is OpenAI's most cost-effective reasoning model, offering o-series chain-of-thought capability at roughly half the price of o3. It is the default reasoning choice when budget is a constraint.

Input Price
$1.10/1M
per 1M tokens
Output Price
$4.40/1M
per 1M tokens
Context Window
200K tokens
max tokens
ELO Score
1350
LMSYS Arena

Pricing Breakdown

VolumeInput CostOutput CostCombined (50/50)
1,000 tokens$0.0011$0.0044$0.0027
10,000 tokens$0.0110$0.0440$0.0275
100,000 tokens$0.1100$0.4400$0.2750
1,000,000 tokens$1.1000$4.4000$2.7500

Strengths

  • Cheapest reasoning model in the OpenAI lineup
  • Strong performance on code and math for the price
  • 200K context window
  • Good latency vs. full o3

Weaknesses

  • Noticeably behind o3 on the hardest reasoning benchmarks
  • Still slower than non-reasoning GPT-5.4 variants

Best For

reasoningcodingmathlow cost

Compare o4-mini With

o4-mini vs GPT-5.4
OpenAI
o4-mini vs Claude Opus 4.7
Anthropic
o4-mini vs Gemini 3.1 Pro
Google
o4-mini vs o3
OpenAI
o4-mini vs Claude Sonnet 4.6
Anthropic
o4-mini vs Gemini 2.5 Pro
Google

Frequently Asked Questions

How much does o4-mini cost?

o4-mini costs $1.10/1M per 1M input tokens and $4.40/1M per 1M output tokens.

What is o4-mini's context window?

o4-mini has a context window of 200K tokens, which means it can process up to 200,000 tokens in a single request.

Is o4-mini open source?

No, o4-mini is a proprietary model by OpenAI and is not open source.

What is o4-mini best used for?

o4-mini is best suited for: reasoning, coding, math, low-cost. Cheapest reasoning model in the OpenAI lineup.

What is o4-mini's ELO score?

o4-mini has an ELO score of 1350 on the LMSYS Chatbot Arena leaderboard, placing it among top-tier models.