Meta: Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instruct

Created Jul 23, 2024131,072 context
$0.015/M input tokens$0.02/M output tokens

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.

Providers for Llama 3.1 8B Instruct

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

DeepInfra (Turbo)
US
fp8
Context
131K
Max Output
16K
Input
$0.015
Output
$0.02
inference.net
US
fp16
Context
16K
Max Output
16K
Input
$0.02
Output
$0.03
NovitaAI
US
fp8
Context
16K
Max Output
16K
Input
$0.02
Output
$0.05
Nebius AI Studio
DE
fp8
Context
131K
Max Output
131K
Input
$0.02
Output
$0.06
Lambda
US
bf16
Context
131K
Max Output
131K
Input
$0.025
Output
$0.04
DeepInfra
US
bf16
Context
131K
Max Output
16K
Input
$0.03
Output
$0.05
    Meta: Llama 3.1 8B Instruct – Provider Status | OpenRouter