Llama-3.3-8B-Instruct

Llama-3.3-8B-Instruct: a llama model from llama, ~128K context, knowledge cutoff 2023-12

Published
scheduleReleasedDecember 6, 2024

Llama-3.3-8B-Instruct is a llama model from llama (~128K context, input around $0/1M tokens). Suitable for assistants, content generation, knowledge Q&A and business automation

starsCapabilities

codeFunction calling

paymentsContext and pricing

Context limit128,000
Max output4,096
Knowledge cutoff2023-12
Input price$0/ 1M tokens
Output price$0/ 1M tokens

descriptionOverview

Overview

Llama-3.3-8B-Instruct is provided by llama, model ID llama-3.3-8b-instruct

Key specs

  • Context: 128K tokens
  • Max output: 4.1K tokens
  • Knowledge cutoff: 2023-12
  • Input price: $0/1M
  • Output price: $0/1M

Best for

Consider Llama-3.3-8B-Instruct when comparing context length, pricing, multimodal support and relay availability

lightbulbUse cases

  • Assistants and customer support
  • Content generation and rewriting
  • Knowledge Q&A and summarization
  • Structured extraction

thumb_upStrengths

  • Large context window (~128K)
  • Open weights, can be self-hosted

infoLimitations

  • Knowledge cutoff 2023-12; newer facts need external retrieval
  • Pricing and availability vary by upstream and relay; verify with official docs and tests

linkReferences

This content is compiled from official documentation and public sources. Always refer to official documentation for final details