LLM Reference

Llama 3.1 405B Instruct

About

Llama 3.1 405B Instruct is Meta's advanced large language model released on July 23, 2024, featuring 405 billion parameters. It utilizes an optimized transformer architecture with supervised fine-tuning and reinforcement learning for enhanced instruction-following capabilities. The model supports multiple languages, was trained on 15 trillion tokens, and fine-tuned with 25 million synthetic examples. It excels in multilingual dialogue and text generation, making it ideal for assistant-like applications. Llama 3.1 incorporates robust safety measures and ethical considerations, outperforming many existing models on various industry benchmarks. AI engineers can access the model via its Hugging Face page for implementation in diverse NLP tasks.

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(10)

ProviderInput (per 1M)Output (per 1M)Type
OctoAI API$3$9
Serverless
Together AI API$5$15
Serverless
Fireworks AI Platform$3$3
Serverless
IBM watsonx$5$35
Serverless
Scale AI GenAI Platform
Serverless
NVIDIA NIM
Provisioned
GroqCloud
Serverless
Azure OpenAI$5.33$16
Provisioned
Databricks Foundation Model Serving
Provisioned
Hyperbolic AI Inference
Serverless

Specifications

FamilyLlama 3.1
Released2024-07-23
Parameters405B
Context128K
ArchitectureDecoder Only
Specializationgeneral