o1-preview-2024-09-12

reasoningdeprecatedproprietary

Research preview of the o1 series of models, trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user.

Intelligence
Reasoning
Speed
Context
128K
Max output
33K
Input price
$15/1M tokens
Output price
$60/1M tokens
Alias ofo1-preview

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Provider OpenAI
Creator openai
Familyo1
Licenseproprietary
Statusdeprecated
Typereasoning
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window128K tokens
Max input—
Max output33K tokens
Reasoning tokensYes
Knowledge cutoff
Release date
Deprecation date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.openai.com/v1/chat/completions
AssistantsPOST
Persistent assistants with tools and fileshttps://api.openai.com/v1/assistants

Pricing

Text tokensPer 1M tokens
InputCached inputOutput
Standard$15$7.5$60

Family Comparison: o1

ModelContextMax outPricing
o1-mini128K66K$1.1$4.4
o1 Preview128K33K$15$60
o1200K100K$15$60
o1-pro200K100K$150$600

API

GET/v1/models/openai/o1-preview-2024-09-12