Mixtral 8x22B Instruct Check detailed information and pricing for AI models
Context Length 65,536 tokens, mistralai from provided
65,536
Context Tokens
$0.90
Prompt Price
$0.90
Output Price
10/16
Feature Support
Model Overview
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding, and reasoning - large context length (64k) - fluency in English, French, Italian, German, and Spanish See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/). #moe
Basic Information
Developer
mistralai
Model Series
Mistral
Release Date
2024-04-17
Context Length
65,536 tokens
Variant
standard
Pricing Information
Prompt Tokens
$0.90 / 1M tokens
Completion Tokens
$0.90 / 1M tokens
Data Policy
Supported Features
Supported (10)
Top K
Frequency Penalty
Presence Penalty
Repetition Penalty
Response Format
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Unsupported (6)
Image Input
Seed
Min P
Reasoning
Web Search Options
Top A
Actual Usage Statistics
#168
Out of 345 total models
686.27M
Total Tokens Last 30 Days
22.88M
Daily Average Usage
20%
Weekly Usage Change