Home/Models/o1

o1

by OpenAI· Released 2024-09
Official Docs ↗

o1 is OpenAI's reasoning model that uses extended chain-of-thought to solve hard problems. It excels at math, science, and complex logical reasoning, but at a significant cost and latency premium over GPT-4o.

Input Price
$15.00/1M
per 1M tokens
Output Price
$60.00/1M
per 1M tokens
Context Window
200K tokens
max tokens
ELO Score
1350
LMSYS Arena

Pricing Breakdown

VolumeInput CostOutput CostCombined (50/50)
1,000 tokens$0.0150$0.0600$0.0375
10,000 tokens$0.1500$0.6000$0.3750
100,000 tokens$1.5000$6.0000$3.7500
1,000,000 tokens$15.0000$60.0000$37.5000

Strengths

  • Best-in-class reasoning on complex problems
  • Exceptional at math, science, and formal logic
  • Large 200K context window
  • Highest quality for research and analysis

Weaknesses

  • Very expensive — highest cost per token in OpenAI lineup
  • Slow — "thinks" before responding (high latency)

Best For

reasoningmathresearchcoding

Compare o1 With

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

Frequently Asked Questions

How much does o1 cost?

o1 costs $15.00/1M per 1M input tokens and $60.00/1M per 1M output tokens.

What is o1's context window?

o1 has a context window of 200K tokens, which means it can process up to 200,000 tokens in a single request.

Is o1 open source?

No, o1 is a proprietary model by OpenAI and is not open source.

What is o1 best used for?

o1 is best suited for: reasoning, math, research, coding. Best-in-class reasoning on complex problems.

What is o1's ELO score?

o1 has an ELO score of 1350 on the LMSYS Chatbot Arena leaderboard, placing it among top-tier models.