GPT-3.5 Turbo Instruct

GPT-3.5 Turbo Instruct

GPT-3.5 Turbo Instruct

by

OpenAI

Model ID:

gpt-3.5-turbo-instruct

Use This Model

Model Overview

FAQs

Related Links

Overview

ChatGPT 3.5 Turbo is a highly efficient variant within OpenAI's GPT-3.5 family, offering optimized performance for fast and cost-effective applications. It maintains a strong balance between intelligence and responsiveness, making it ideal for real-time interactions, large-scale deployments, and dynamic conversational tasks.

Specializations

  • Built upon InstructGPT, this model specializes in following detailed instructions and generating precise outputs.

  • Enhances performance in question-answering scenarios, making it ideal for educational tools and customer support.

  • Cost-efficient while maintaining high-quality text generation capabilities.

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: 'gpt-3.5-turbo-instruct',

});

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

Live API Statistics and Performace Metrics

LMSys Arena Elo Score:

1117

Arena Score

LMSys Leaderboard Rank:

72

Arena Rank

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

HumanEval Leaderboard Score:

Leaderboard Score

48.1

%

A specific benchmark score measuring the model's accuracy in executing code generations.

Model Specifications

Release Date:

18/9/2023

Model Variants:

gpt-3.5-turbo-instruct-0914

Max. Context Tokens:

4K

Max. Output Tokens:

4K

Knowledge Cut-Off Date:

September 2021

MMLU:

70

%

License:

Proprietary

LMSys Elo Score

1117

Berkeley Function Calling Ability Score:

NaN

Pricing

$/Million Input Tokens

$

1.5

$/Million Output Tokens

$

2

Live updates via Portkey Pricing API. Coming Soon...

© 2024 Portkey, Inc. All rights reserved