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/grok-2";
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.
Grok-2
xAI's Grok-2 represents a significant advancement in language model technology, offering state-of-the-art reasoning capabilities. As a successor to Grok-1.5, Grok-2 demonstrates substantial improvements in chat, coding, and reasoning. Alongside Grok-2, xAI is introducing Grok-2 mini, a smaller model that balances speed and quality.
Key Features of Grok-2
-
Superior Performance: Grok-2 outperforms both Claude 3.5 Sonnet and GPT-4-Turbo on the LMSYS leaderboard. An early version of Grok-2 was tested under the name "sus-column-r".
-
Enhanced Reasoning: Grok-2 showcases improvements in reasoning with retrieved content and tool use. It can accurately identify missing information, reason through sequences of events, and disregard irrelevant posts.
-
Benchmark Results: Grok-2 demonstrates competitive performance in graduate-level science knowledge (GPQA), general knowledge (MMLU, MMLU-Pro), and math competition problems (MATH). It also excels in vision-based tasks, achieving state-of-the-art results in visual math reasoning (MathVista) and document-based question answering (DocVQA)
Additional Information
-
Multimodal Understanding: xAI plans to release a preview of multimodal understanding as a core feature of Grok on š¯•¸ and via the API.
-
Continued Innovation: xAI is focused on advancing core reasoning capabilities and has plans for further developments.
Popular Models
