o1-preview

o1-preview

o1-preview

by

OpenAI

Model ID:

o1-preview

Use This Model

Model Overview

FAQs

Related Links

Overview

The O1 model is a sophisticated AI designed for advanced reasoning tasks. It excels in handling complex inquiries, particularly in coding, mathematics, and scientific problem-solving. This model employs a unique training method that emphasizes reinforcement learning, enabling it to process questions through a "chain of thought" approach similar to human reasoning. The O1 model is noted for its high accuracy and ability to tackle challenging problems effectively, making it suitable for users requiring deep analytical capabilities. However, it comes at a higher cost compared to its counterparts, reflecting its advanced functionalities and broader knowledge base.

Specializations

  • Advanced Reasoning Capabilities: Demonstrates superior performance in complex reasoning tasks.

  • Strong Factual Knowledge: Possesses a broad knowledge base across various domains.

  • Higher Computational Cost: Requires more computational resources compared to smaller models.

Integration Guide (Javascript)

To use this model through Portkey, follow these steps:

1. Install Portkey SDK:

npm install --save portkey-ai

2. Set up client with Portkey:

import OpenAI from 'openai';

import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const openai = new OpenAI({

  apiKey: 'OPENAI_API_KEY',

  baseURL: PORTKEY_GATEWAY_URL,

  defaultHeaders: createHeaders({

    provider: "openai",

    apiKey: "PORTKEY_API_KEY"

  })

});

3. Make a request:

const chatCompletion = await openai.chat.completions.create({

  messages: [{ role: 'user', content: 'Say this is a test' }],

  model: 'o1-preview',

});

console.log(chatCompletion.choices[0].message.content);

Live API Statistics and Performace Metrics

LMSys Arena Elo Score:

1355

Arena Score

LMSys Leaderboard Rank:

1

Arena Rank

Evaluates LLMs through a combination of user feedback and automated scoring systems.

Model Specifications

Release Date:

12/9/2024

Model Variants:

o1-preview-2024-09-12

Max. Context Tokens:

128K

Max. Output Tokens:

32K

Knowledge Cut-Off Date:

October 2023

License:

Proprietary

LMSys Elo Score

1355

© 2024 Portkey, Inc. All rights reserved