GPT-4o (August 6th, 2024)
by
OpenAI
Model ID:
gpt-4o-2024-08-06
Overview
GPT-4o is an advanced "omni model" that accepts input in text, audio, image, and video formats, and generates outputs in text, audio, and image. It matches GPT-4 Turbo's performance on English text and code, while showing significant improvements in non-English languages, vision, and audio understanding. GPT-4o is faster and 50% cheaper in the API compared to GPT-4. It can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, comparable to human response times.
Specializations
Multimodal Capabilities: GPT-4o can process and generate content across multiple modalities - accepting text, audio, image, and video inputs, and producing text, audio, and image outputs.
Improved Language Performance: While matching GPT-4 Turbo on English and code, GPT-4o shows significant improvements in non-English languages, narrowing the performance gap between English and historically underrepresented languages.
Fast Audio Response: GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is comparable to human response times in conversation.
Cost-Effective: The model is 50% cheaper in the API compared to its predecessor, making it more accessible for developers and businesses.
Enhanced Medical and Scientific Capabilities: GPT-4o demonstrates improved performance on medical knowledge benchmarks and shows promise in tasks involving specialized scientific reasoning, potentially accelerating research and innovation.
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-4o-2024-08-06',
});
console.log(chatCompletion.choices[0].message.content);
Live API Statistics and Performace Metrics
LMSys Arena Elo Score:
1263
Arena Score
LMSys Leaderboard Rank:
8
Arena Rank
Evaluates LLMs through a combination of user feedback and automated scoring systems.
HumanEval Leaderboard Score:
Leaderboard Score
90.2
%
A specific benchmark score measuring the model's accuracy in executing code generations.
Model Specifications
Release Date:
6/8/2024
Model Variants:
gpt-4o-2024-08-06
Max. Context Tokens:
128K
Max. Output Tokens:
16K
Knowledge Cut-Off Date:
October 2023
MMLU:
88.7
%
License:
Proprietary
Technical Report/Model Card:
LMSys Elo Score
1263
Berkeley Function Calling Ability Score:
NaN
Pricing
$/Million Input Tokens
$
2.5
$/Million Output Tokens
$
10
Live updates via Portkey Pricing API. Coming Soon...
© 2024 Portkey, Inc. All rights reserved