Back to Models
openai logo
openai/o1
Not Available

o1

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).

12/17/2024
200,000 tokens
#44 Text to Image (Overall)

Specifications

Modalities

Input
text
image
file
Output
text

Supported Parameters

max_tokens
response_format
seed
structured_outputs
tool_choice
tools

Max Output Tokens

100,000

Frequently asked questions

Is o1 available on FastMetal?
Not at the moment. GPT-5.6 Sol, from the same lab, is available on the FastMetal API today.
What is the context window of o1?
200,000 tokens, shared between the prompt and the response.
How does o1 rank?
#167 on the public arena's Japanese board (ELO 1,277). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,337
#221
JapaneseELO: 1,277
#167
ChineseELO: 1,350
#219
KoreanELO: 1,252
#197
EnglishELO: 1,353
#225
frenchELO: 1,324
#213
germanELO: 1,300
#203
spanishELO: 1,335
#193
russianELO: 1,310
#230
MathELO: 1,362
#190
CodingELO: 1,387
#211
Creative WritingELO: 1,281
#247
Instruction FollowingELO: 1,332
#208
Hard PromptsELO: 1,360
#212
Multi-TurnELO: 1,324
#229
Vision
OverallELO: 1,193
#78
Text to Image
OverallELO: 1,117
#44