Llama 3.1 8B
Language modelPrevious generationOpen weightsCard summarizedThe Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases
Open weights (static model, still published)● Re-checked 12 Oct 2026 · 10 facts · 0 corrections · 1 unconfirmedSource: Llama 3.1 Model Card (MODEL_CARD.md)
Use it via API
Where to call it
- Self-host (weights)
meta-llama/Llama-3.1-8B-Instruct - Amazon Bedrock
Llama 3.1 8B - DeepInfra
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
Good for
- Commercial and research use in multiple languages
- Assistant-like chat (instruction-tuned)
- Using model outputs to improve other models, including synthetic data generation and distillation
Overview
Llama 3.1 8B
The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases
- Cost
- $0.02 host
- Context
- 128K
- Cheapest host
- $0.02 / $0.04
- Max output
- —
- Knows up to
- December 2023
- Released
- 23 Jul 2024
Llama 3.1 8B is the smallest instruction-tuned, text-only model in Meta's Llama 3.1 collection (8B, 70B, 405B), optimized for multilingual dialogue. It uses an optimized transformer with grouped-query attention, a 128K context and 15T+ pretraining tokens. Model Information
meta-llama/Llama-3.1-8B-Instruct- Input / output per 1M
- $0.02 / $0.04 via DeepInfra
- Context window
- 128K
- Max output
- —
- Knows up to
- December 2023
- Reasoning
- —
- Weights
- Open · Llama 3.1 Community License
About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Meta's Llama 3.1 Model Card (MODEL_CARD.md). Every claim carries its source page.