Mixtral 8x22B Instruct

Mixtral 8x22B Instruct

Developer	Mistral AI
Release date	April 17, 2024
Context window	66K tokens
Max output	52K tokens
Input	Text, file
Output	Text
Knowledge cutoff	2024-01-31
Weights	Open weights
Website	mistral.ai
Links	Model card Docs Hugging Face

Part of a series on

input: $2.00
cached: $0.20
output: $6.00
Context: 66Ktokens
Released: 2y ago
Size: 141Bparameters

Specifications

Model

Developer: Mistral AI
Type: Language model
Released: April 17, 2024
Model ID: mistralai/mixtral-8x22b-instruct

Capabilities

Input → output: Text, file → Text
Max output: 52K tokens
Tokenizer: Mistral
Knowledge cutoff: 2024-01-31

Weights

Openness: Open weights
Size: 141B
Hugging Face: mistralai/Mixtral-8x22B-Instruct-v0.1

Sources:models.devOpenRouter

Metadata synced Nov 3, 2026, 11:17 PM UTC

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.