LLM Reference

Mixtral 8x7B

About

Mixtral 8x7B, developed by Mistral AI, features a cutting-edge Mixture of Experts (MoE) architecture, utilizing eight experts with seven billion parameters each, yielding a total of 46.7 billion parameters. This architecture activates only two experts per token, allowing for efficient processing and a 6x faster inference rate compared to Llama 2 70B. The model excels in performance, surpassing Llama 2 70B and competing with GPT-3.5 on numerous benchmarks. It supports multiple languages and can handle context up to 32,000 tokens, enhancing understanding of lengthy text. Designed for diverse tasks, it is strong in code generation and available under a permissive Apache 2.0 license, promoting community engagement. Compatible with various optimization tools, its weights are easily deployable, with Mistral AI continuing to improve its capabilities through performance optimizations and fine-tuning efforts.

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(18)

ProviderInput (per 1M)Output (per 1M)Type
Databricks Foundation Model Serving$0.5$1
Serverless
NVIDIA NIM
Provisioned
GCP Vertex AI
Serverless
AWS Bedrock$0.45$0.7
Serverless
GroqCloud$0.24$0.24
Serverless
Snowflake Cortex$0.44$0.44
Serverless
OctoAI API$0.45$0.45
Serverless
Fireworks AI Platform$0.5$0.5
Serverless
deepinfra API
Serverless
Mistral AI Le Plateforme
Serverless
Baseten API
Serverless
Lepton AI API
Serverless
Replicate API
Serverless
Azure OpenAI
Provisioned
Alibaba Cloud PAI-EAS
Serverless
Perplexity Labs
Serverless
IBM watsonx$0.6$0.6
Serverless
Scale AI GenAI Platform
Serverless

Specifications

FamilyMixtral
Released2023-12-11
Parameters8x7B
Context32K
ArchitectureMixture of Experts
Specializationgeneral