Name: Mixtral 8x22B Instruct API
Brand: Mistral AI

Overview

Mixtral-8x22B-Instruct-v0.1 Description

Basic Information

Model Name: Mixtral-8x22B-Instruct-v0.1
Developer/Creator: Mistral AI
Release Date: April 17, 2024
Version: 0.1
Model Type: Large Language Model (LLM)

Overview:

Mixtral-8x22B-Instruct-v0.1 is a cutting-edge large language model designed for instruction-following tasks. Built on a Mixture of Experts (MoE) architecture, this model is optimized for efficiently processing and generating human-like text based on detailed prompts.

Key Features:

Mixture of Experts Architecture: Utilizes eight specialized models, each with 141 billion parameters, to enhance processing speed and efficiency.
Fine-Tuned for Instructions: Specifically optimized to follow detailed instructions accurately, making it suitable for various applications.
High Throughput: Capable of processing 98 tokens per second, allowing for rapid response generation.
Multilingual Capabilities: Supports multiple languages, facilitating use in diverse linguistic contexts.
Robust Performance: Designed to handle complex tasks, including text generation, question answering, and conversational AI.

Intended Use:

The model is intended for developers and researchers looking to implement advanced natural language processing capabilities in applications such as chatbots, virtual assistants, and automated content generation tools.

Language Support:

Mixtral-8x22B-Instruct-v0.1 supports multiple languages, enhancing its usability in global applications.

Technical Details

Architecture:

The model employs a Mixture of Experts architecture that activates different subsets of parameters based on input demands. This architecture allows for efficient computation while maintaining high-quality output.

Training Data:

The model was trained on a diverse dataset consisting of high-quality text from various domains to ensure robust performance across different topics.

Data Source and Size: The training dataset includes a wide range of text sources, although specific sizes are not disclosed.
Knowledge Cutoff: The model's knowledge is current as of September 2021.
Diversity and Bias: The training data was curated to minimize biases while maximizing diversity in topics and styles, enhancing the model's robustness.

Performance Metrics and Comparison to Other Models:

Mixtral-8x22B-Instruct-v0.1 has demonstrated impressive performance metrics:

‍

Usage

Code samples

The model is available on the AI/ML API platform as "Mixtral 8x22B Instruct" .

Ethical Considerations

Mistral AI emphasizes ethical considerations in AI development by promoting transparency regarding the model's capabilities and limitations. The organization encourages responsible usage to prevent misuse or harmful applications of generated content.

Licensing

The Mixtral models are available under an open-source license that allows both research and commercial usage rights while ensuring compliance with ethical standards.

‍

Get Mixtral 8x22B Instruct API here.

Use cases

Chatbots and virtual assistants
Language translation
Text summarization
Creative content generation
Coding and programming assistance
Mathematical problem solving
Technical explanations
Content moderation and filtering
Application development with function calls

How to use Mixtral 8x22B Instruct API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to mistralai/mixtral-8x22b-instruct.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "mistralai/mixtral-8x22b-instruct",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "mistralai/mixtral-8x22b-instruct",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/mixtral-8x22b-instruct","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.