Home/Models/o3

o3

by OpenAI· Released 2025-04
Official Docs ↗

o3 is OpenAI's most capable reasoning model, achieving state-of-the-art scores on ARC-AGI and math benchmarks. It improves on o1 with better cost efficiency and stronger agentic capabilities.

Input Price
$10.00/1M
per 1M tokens
Output Price
$40.00/1M
per 1M tokens
Context Window
200K tokens
max tokens
ELO Score
1380
LMSYS Arena

Pricing Breakdown

VolumeInput CostOutput CostCombined (50/50)
1,000 tokens$0.0100$0.0400$0.0250
10,000 tokens$0.1000$0.4000$0.2500
100,000 tokens$1.0000$4.0000$2.5000
1,000,000 tokens$10.0000$40.0000$25.0000

Strengths

  • Highest reasoning benchmark scores of any model
  • Better cost-efficiency than o1 at similar quality
  • Superior at agentic and multi-step tasks
  • 200K context window

Weaknesses

  • Still expensive for most use cases
  • Slower than non-reasoning models

Best For

reasoningmathcodingresearch

Compare o3 With

o3 vs DeepSeek R1
DeepSeek
o3 vs o1
OpenAI
o3 vs Gemini 2.0 Flash
Google
o3 vs DeepSeek V3
DeepSeek
o3 vs Claude Sonnet 4.6
Anthropic
o3 vs Claude 3.5 Sonnet
Anthropic

Frequently Asked Questions

How much does o3 cost?

o3 costs $10.00/1M per 1M input tokens and $40.00/1M per 1M output tokens.

What is o3's context window?

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

Is o3 open source?

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

What is o3 best used for?

o3 is best suited for: reasoning, math, coding, research. Highest reasoning benchmark scores of any model.

What is o3's ELO score?

o3 has an ELO score of 1380 on the LMSYS Chatbot Arena leaderboard, placing it among top-tier models.