Home/Models/o3-mini

o3-mini

by OpenAI· Released 2025-01
Official Docs ↗

o3-mini is OpenAI's compact reasoning model released January 2025, offering three effort levels (low, medium, high) to balance cost and quality. While largely superseded by o4-mini, it remains available and popular for STEM reasoning tasks at a competitive price.

Try in OpenAI Playground

Free trial credits for new accounts

Try free
Input Price
$1.10/1M
per 1M tokens
Output Price
$4.40/1M
per 1M tokens
Context Window
200K tokens
max tokens
ELO Score
1340
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

  • Strong reasoning at a low price point
  • 200K context window
  • Three effort levels (low/medium/high) for cost control
  • Well-suited for STEM and coding tasks

Weaknesses

  • Superseded by o4-mini for most use cases
  • No image input support

Best For

reasoningmathcodinglow cost

Compare o3-mini With

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

Frequently Asked Questions

How much does o3-mini cost?

o3-mini costs $1.10/1M per 1M input tokens and $4.40/1M per 1M output tokens.

What is o3-mini's context window?

o3-mini has a context window of 200K tokens, which means it can process up to 200,000 tokens in a single request.

Is o3-mini open source?

No, o3-mini is a proprietary model by OpenAI and is not open source.

What is o3-mini best used for?

o3-mini is best suited for: reasoning, math, coding, low-cost. Strong reasoning at a low price point.

What is o3-mini's ELO score?

o3-mini has an ELO score of 1340 on the LMSYS Chatbot Arena leaderboard, placing it among top-tier models.