Llama 3.2 1B Instruct

Name: Llama 3.2 1B Instruct
Author: Novita AI

llama3.21B

The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).

Context

131K

Max output

32K

Input price

$0.02/1M tokens

Output price

$0.02/1M tokens

Capabilities

Show unsupported (3)

Reasoning & Interaction

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Fine-tuning

Details

Model IDmeta-llama/llama-3.2-1b-instruct

ProviderNovita AI

CreatorMeta Llama

Familyllama-3.2

Licensellama3.2

Statusactive

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters1B

Architecture—

Context window131K tokens

Max input—

Max output32K tokens

Reasoning tokens—

Knowledge cutoff2023-12

Release date2024-11-26

Sourceofficial

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input

$0.02

Output

$0.02

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: llama-3.2

Model	Caps	Perf	Speed	Context	Max out	Pricing
Llama 3.2 1B Instruct	TJJMSF	—	—	131K	32K	$0.02$0.02
Llama 3.2 3B Instruct	TSF	—	—	33K	32K	$0.03$0.05

API

GET/v1/models/novita/meta-llama/llama-3.2-1b-instruct