Mixtral 8x22B Instruct API

Advanced Mixtral-8x22B-Instruct-v0.1 excels in efficient, instruction-driven task performance across sectors.

Modalities: TextText
Context window: 64K tokens
Released: Apr 17, 2024
Status: Deprecated

Mixtral 8x22B Instruct overview

Mixtral 8x22B Instruct by Mistral AI

Mixtral-8x22B-Instruct-v0.1 API combines a Mixture-of-Experts architecture with instruction tuning for fast, efficient handling of complex tasks.

Mixtral 8x22B Instruct specs

Model ID: mistralai/mixtral-8x22b-instruct
Developer: Mistral AI
Context window: 65,536 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Basic Information

Model Name: Mixtral-8x22B-Instruct-v0.1
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.

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.

Use cases

Chatbots and virtual assistants
Coding and programming assistance
Content moderation and filtering
Application development with function calls

Capabilities

Function calling
Streaming
Structured outputs
Reasoning

Mixtral 8x22B Instruct benchmarks by Artificial Analysis

See how Mixtral 8x22B Instruct scores on independent evaluations. Data retrieved Nov 3, 2026.

Humanity's Last Exam#404 / 4584%Score GPQA Diamond#383 / 43933.2%Score LiveCodeBench#214 / 26314.8%Score MMLU-Pro#213 / 26853.7%Score

Benchmark results

Compare 14 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

MATH-500

Competition mathematics problems.

Mixtral 8x22B Instruct API pricing

Mixtral 8x22B Instruct pricing in US dollars
Usage	Price	Unit
Input	$2.12	1M tokens
Output	$6.35	1M tokens
Cached input	$0.2116	1M tokens

Mixtral 8x22B Instruct is deprecated on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Mixtral 8x22B Instruct vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Mixtral 8x22B Instruct	$2.12	$6.35
Small 4	$0.1984	$0.7935
Mistral Large 4	$1.36	$4.18
Aion-3.0	$3.17	$6.35
Medium 3.5	$1.59	$7.93

How to use the Mixtral 8x22B Instruct API

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl '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": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "mistralai/mixtral-8x22b-instruct",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Mixtral 8x22B Instruct FAQ

What is the context window of Mixtral 8x22B Instruct?

Mixtral 8x22B Instruct has a 65,536 tokens context window.

What inputs and outputs does Mixtral 8x22B Instruct support?

Mixtral 8x22B Instruct takes image, text as input and returns text.

What is the model ID for Mixtral 8x22B Instruct?

Use mistralai/mixtral-8x22b-instruct as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

How much does Mixtral 8x22B Instruct cost?

Mixtral 8x22B Instruct is priced at input $2.7508 / 1M tokens, output $8.2524 / 1M tokens, cached input $0.27508 / 1M tokens.

Does Mixtral 8x22B Instruct support streaming?

Yes, Mixtral 8x22B Instruct can stream responses as they are generated.

Can Mixtral 8x22B Instruct read images?

Yes, Mixtral 8x22B Instruct accepts image input alongside text.

Who created Mixtral 8x22B Instruct?

Mixtral 8x22B Instruct was built by Mistral AI.

Start building with Mixtral 8x22B Instruct

Get API key

Mixtral 8x22B Instruct API

mistralai/mixtral-8x22b-instruct

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl '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": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "mistralai/mixtral-8x22b-instruct",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Mixtral 8x22B Instruct API

Mixtral 8x22B Instruct overview

Mixtral 8x22B Instruct by Mistral AI

Mixtral 8x22B Instruct specs

Basic Information

Overview:

Key Features:

Intended Use:

Language Support:

Architecture:

Use cases

Capabilities

Mixtral 8x22B Instruct benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

LiveCodeBench

MMLU-Pro

MATH-500

Mixtral 8x22B Instruct API pricing

Mixtral 8x22B Instruct vs other models: token prices

How to use the Mixtral 8x22B Instruct API

Build with your agent

1Get your API key

2Make your first request

Related articles

Mixtral 8x22B Instruct FAQ

Start building with Mixtral 8x22B Instruct

Mixtral 8x22B Instruct API

Build with your agent

1Get your API key

2Make your first request

Mixtral 8x22B Instruct API

Mixtral 8x22B Instruct overview

Mixtral 8x22B Instruct by Mistral AI

Mixtral 8x22B Instruct specs

Basic Information

Overview:

Key Features:

Intended Use:

Language Support:

Architecture:

Use cases

Capabilities

Benchmark results

Humanity's Last Exam

GPQA Diamond

LiveCodeBench

MMLU-Pro

MATH-500

Mixtral 8x22B Instruct API pricing

Mixtral 8x22B Instruct vs other models: token prices

How to use the Mixtral 8x22B Instruct API

Build with your agent

1Get your API key

2Make your first request

Models similar to Mixtral 8x22B Instruct

Mistral Large 4

Mistral OCR 4

Mistral OCR 3

Fugu Max

Gemini 3.1 Pro Preview Custom Tools

Gemini Pro Latest

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Mixtral 8x22B Instruct FAQ

Start building with Mixtral 8x22B Instruct