Llama 3.1 8B Instruct (Meta)

View on Meta View on Hugging Face View on OpenRouter

Verified provider routes accept text input and produce text output. Supported combinations depend on the provider route.

Source 1 · Source 2

Identity and capabilities

Status: Deprecated
Local execution: Available weights · transformers · access approval or licence acceptance required · llama3.1 Hardware requirements and licence restrictions apply.
Context window: 131,072
Maximum output: 117,964
Image input: No
Reasoning: No
Tool calling: Yes
Release date: Jul 23, 2024
First seen: 2026-08-29 19:40:01Z UTC
Last verified: just now

Current offers - prices in USD · per 1M tokens

Prices by provider, service tier, context and offer route
	Amazon Bedrock	Cloudflare	Hugging Face Inference Providers ⊕ 3 routes ▾	OpenRouter
Standard		Deprecated	Novita
Cached input	—	—	—	$0.025
Input	$0.22	$0.282	$0.02	$0.05
Output	$0.22	$0.827	$0.05	$0.08

Hugging Face Inference Providers · 3 routes — show all prices

The main table shows Novita: the lowest available starting token price for 2 input tokens per output token. Other input lengths, service tiers and usage ratios may favour another route.

Prices by provider, service tier, context and offer route
	Novita	DeepInfra	Nscale
Input	$0.02	$0.02	$0.06
Output	$0.05	$0.05	$0.06

Active promotions

No officially confirmed promotion applies to this model.

Recent price changes

No price changes in the last 7 days.