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/mixtral-8x22b-instruct";
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);
}
})();
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.
Mixtral 8x22B is the latest open model by Mistral AI. It sets a new standard for performance and efficiency within the AI community. It is a sparse Mixture-of-Experts (SMoE) model that uses only 39B active parameters out of 141B, offering unparalleled cost efficiency for its size.
Mixtral 8x22B comes with the following strengths:
It is fluent in English, French, Italian, German, and Spanish It has strong mathematics and coding capabilities It is natively capable of function calling; along with the constrained output mode implemented on la Plateforme, this enables application development and tech stack modernisation at scale Its 64K tokens context window allows precise information recall from large documents
We believe in the power of openness and broad distribution to promote innovation and collaboration in AI.
We are, therefore, releasing Mixtral 8x22B under Apache 2.0, the most permissive open-source licence, allowing anyone to use the model anywhere without restrictions.