1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
const axios = require('axios');
const api_key = "YOUR API-KEY";
const url = "https://api.segmind.com/v1/gpt-4.5-preview";
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);
}
})();Attributes
An array of objects containing the role and content
Could be "user", "assistant" or "system".
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.
The GPT-4.5 Preview model, codenamed Orion, is OpenAI’s largest and most advanced general-purpose large language model (LLM) to date, released as a research preview on February 27, 2025. Built on the GPT architecture, it emphasizes scaling unsupervised learning, resulting in a model with a broader knowledge base, enhanced conversational abilities, and improved emotional intelligence (EQ). GPT-4.5 is designed for natural, human-like interactions, making it a significant step forward in conversational AI.
Capabilities and Strengths: GPT-4.5 excels in tasks requiring creativity, nuanced understanding, and natural conversation. It outperforms its predecessor, GPT-4o, in writing assistance, programming support, and practical problem-solving due to its ability to recognize patterns, draw connections, and follow user intent with greater precision. Early testing shows a 62.5% score on OpenAI’s SimpleQA benchmark, surpassing GPT-4o’s 38.6%, and a reduced hallucination rate (37.1% vs. 59.8% for GPT-4o), making it more reliable for factual queries. Its conversational tone is warmer and more intuitive, with human testers preferring it over GPT-4o for everyday and creative tasks, such as crafting compelling headlines or providing empathetic advice. The model supports file and image uploads, real-time search, and ChatGPT’s canvas tool, enhancing its utility for diverse applications like tutoring, marketing copy, and light coding.
Limitations and Weaknesses: Despite its advancements, GPT-4.5 is not a frontier model and falls short in complex reasoning tasks compared to OpenAI’s o1 and o3 models. It scores lower on math (36.7% on AIME) and science benchmarks than o3-mini, limiting its effectiveness for logic-heavy or technical workflows. The model’s compute-intensive nature makes it expensive, raising questions about its long-term API availability. It also lacks multimodal features like Voice Mode, video, and screen sharing, restricting its versatility. Additionally, its performance on coding benchmarks like SWE-Bench (38%) is decent but trails competitors like Anthropic’s Claude 3.7 Sonnet. GPU shortages have delayed broader access, highlighting scalability challenges.
Conclusion: GPT-4.5 is a conversational powerhouse, ideal for creative and human-facing tasks, but its high cost and weaker reasoning capabilities make it less suited for specialised technical applications. OpenAI’s ongoing evaluation will shape its future role.
Popular Models
