GPT 4

GPT-4 outperforms both previous large language models and as of 2023, most state-of-the-art systems (which often have benchmark-specific training or hand-engineering). On the MMLU benchmark, an English-language suite of multiple-choice questions covering 57 subjects, GPT-4 not only outperforms existing models by a considerable margin in English, but also demonstrates strong performance in other languages.

Playground API Pricing

API

If you're looking for an API, you can choose from your desired programming language.

POST

const axios = require('axios');

const api_key = "YOUR API-KEY";
const url = "https://api.segmind.com/v1/gpt-4";

const data = {
  
  "messages": [
    {
            "role": "user",
            "content": "tell me a joke on cats"
        },
        {
            "role": "assistant",
            "content": "here is a joke about cats..."
        },
       {
            "role": "user",
            "content": "now a joke on dogs"
        }
  ]
};

(async function() {
    try {
        const response = await axios.post(url, data, { headers: { 'x-api-key': api_key } });
        console.log(response.data);
    } catch (error) {
        console.error('Error:', error.response.data);
    }
})();

RESPONSE

application/json

HTTP Response Codes

200 - OKResponse Generated

401 - UnauthorizedUser authentication failed

404 - Not FoundThe requested URL does not exist

405 - Method Not AllowedThe requested HTTP method is not allowed

406 - Not AcceptableNot enough credits

500 - Server ErrorServer had some issue with processing

Attributes

messagesArray

An array of objects containing the role and content

rolestr

Could be "user", "assistant" or "system".

contentstr

A string containing the user's query or the assistant's response.

To keep track of your credit usage, you can inspect the response headers of each API call. The x-remaining-credits property will indicate the number of remaining credits in your account. Ensure you monitor this value to avoid any disruptions in your API usage.

GPT- 4

GPT-4 is a highly advanced language model that uses a transformer architecture for processing complex linguistic structures. It’s capable of generating human-like text, making it useful for a variety of applications. One of the key features of GPT-4 is its attention mechanism, which allows the model to discern which pieces of data are more relevant than others. This results in more targeted and informative responses, enhancing user interaction.

GPT-4 can handle over 25,000 words of text, allowing for use cases like long-form content creation, extended conversations, and document search and analysis. It surpasses GPT-3.5 in its advanced reasoning capabilities.