mixtral-8x7b-instruct

completions

bydeepinfra

mixtral-8x7b-instruct

completions

Published by: mistralaiProvider:

deepinfra

Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion parameters. Instruct model fine-tuned by Mistral. #moe

Released

Dec 11, 2023

Knowledge

Jun 14, 2023

Context

32768

Input

$0.08 / 1M tokens

Output

$0.24 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Released Dec 11, 2023Knowledge Cutoff: Jun 14, 2023

Context: 32768 Input: $0.08 / 1M tokensOutput: $0.24 / 1M tokensCapabilities: toolsAccepts: textReturns: text

Access mixtral-8x7b-instruct through LangDB AI Gateway

Recommended

Integrate with mistralai's mixtral-8x7b-instruct and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for mixtral-8x7b-instruct

Category Performance Scores:

Academia: Score 15.90 (Top 95% - Rank #328)
Marketing: Score 28.49 (Top 91% - Rank #314)
Programming: Score 4.70 (Top 97% - Rank #335)
Science: Score 30.15 (Top 95% - Rank #328)
Writing: Score 29.01 (Top 92% - Rank #318)

Overall Performance: 21.649500000000003 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	0.00	Top 91%	Mathematics
AA Coding Index	4.70	Top 97%	Programming
AAII	2.60	Top 96%	General
GPQA	29.20	Top 94%	STEM (Physics, Chemistry, Biology)
HLE	4.50	Top 50%	General Knowledge
LiveCodeBench	6.60	Top 94%	Programming
MATH-500	29.90	Top 94%	Mathematics
MMLU-Pro	38.70	Top 94%	General Knowledge
SciCode	2.80	Top 96%	Scientific

GPQA Score: 29.20 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 32768 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

0.0

Mathematics

AA Coding Index

4.7

Programming

AAII

2.6

General

GPQA

29.2

STEM (Physics, Chemistry, Biology)

HLE

4.5

General Knowledge

LiveCodeBench

6.6

Programming

MATH-500

29.9

Mathematics

MMLU-Pro

38.7

General Knowledge

SciCode

2.8

Scientific

Metric	AIME	AA Coding Index	AAII	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	0.0	4.7	2.6	29.2	4.5	6.6	29.9	38.7	2.8

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for mixtral-8x7b-instruct

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="mixtral-8x7b-instruct",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "mixtral-8x7b-instruct",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mixtral-8x7b-instruct",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: mixtral-8x7b-instruct

Provider: deepinfra

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from deepinfra

mixtral-8x7b-instruct

mixtral-8x7b-instruct

Access mixtral-8x7b-instruct through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B

mixtral-8x7b-instruct by deepinfra - AI Model Details, Pricing, and Performance Metrics

mixtral-8x7b-instruct

mixtral-8x7b-instruct

Access mixtral-8x7b-instruct through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B