Overview
GPT-4 Turbo is a variant of the GPT-4 model, optimized for faster and more cost-effective performance. It is designed to handle similar tasks as GPT-4 but with improvements in efficiency, making it more suitable for large-scale deployments and applications where speed and cost are crucial. While GPT-4 Turbo shares many capabilities with GPT-4, it is engineered to deliver these at a lower operational cost, making it a more practical choice for many users while still maintaining a high level of intelligence and capability.
Specializations
Enhanced Factual Knowledge: Offers improved accuracy and factual grounding compared to previous models.
Faster Response Times: Delivers quicker responses, making it more efficient for real-time applications.
Cost-Effective: Provides a balance of performance and affordability.
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-4-turbo',
});
console.log(chatCompletion.choices[0].message.content);
Live API Statistics and Performace Metrics
LMSys Arena Elo Score:
1257
Arena Score
LMSys Leaderboard Rank:
14
Arena Rank
Evaluates LLMs through a combination of user feedback and automated scoring systems.
HumanEval Leaderboard Score:
Leaderboard Score
87.1
%
A specific benchmark score measuring the model's accuracy in executing code generations.
Model Specifications
Release Date:
14/11/2023
Model Variants:
gpt-4-turbo-2024-04-09
Max. Context Tokens:
128K
Max. Output Tokens:
4K
Knowledge Cut-Off Date:
April 2023
MMLU:
86.5
%
License:
Proprietary
LMSys Elo Score
1257
Berkeley Function Calling Ability Score:
NaN
Pricing
$/Million Input Tokens
$
10
$/Million Output Tokens
$
30
Live updates via Portkey Pricing API. Coming Soon...
© 2024 Portkey, Inc. All rights reserved