Meta-Llama-3.1-8B-Instruct

llama8B

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes

Context
131K
Max output
131K
Input price
$0.02/1M tokens
Output price
$0.05/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Fine-tuning

Details

Model IDmeta-llama/Meta-Llama-3.1-8B-Instruct
Provider DeepInfra
Creator Meta Llama
FamilyLlama-3.1
Licensellama
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters8B
Architecture—
Context window131K tokens
Max input—
Max output131K tokens
Reasoning tokens—
Knowledge cutoff
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$0.02
Output
$0.05
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: Llama-3.1

ModelContextMax outPricing
Meta-Llama-3.1-8B-Instruct-Turbo131K—$0.02$0.04
Meta-Llama-3.1-8B-Instruct131K—$0.02$0.05
Meta-Llama-3.1-70B-Instruct-Turbo131K—$0.4$0.4
Meta-Llama-3.1-70B-Instruct131K—$0.4$0.4
Llama-3.1-Nemotron-70B-Instruct131K—$1.2$1.2

API

GET/v1/models/deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct