Mistral: Mixtral 8x7B Instruct

Mistral

Text

Paid

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

Parameters

~47B

Context Window

32,768

tokens

Input Price

$0.08

per 1M tokens

Output Price

$0.24

per 1M tokens

Capabilities

Model capabilities and supported modalities

Performance

Reasoning

Good reasoning with solid logical foundations

Math

Coding

Capable of generating functional code with good practices

Knowledge

Modalities

Input Modalities

text

Output Modalities

text

Visit Official Website

LLM Price Calculator

Calculate the cost of using this model

Input Tokens (0.00000008/token)$0.000120

Output Tokens (0.00000024/token)$0.000720

Common Scenarios:

Input Cost:$0.000120

Output Cost:$0.000720

Total Cost:$0.000840

Estimated usage: 4,500 tokens

Monthly Cost Estimator

Based on different usage levels

Light Usage

$0.0032

~10 requests

Moderate Usage

$0.0320

~100 requests

Heavy Usage

$0.3200

~1000 requests

Enterprise

$3.2000

~10,000 requests

Note: Estimates based on current token count settings per request.

Last Updated: 2025/05/06