Llama 4 Scout Instruct

Name: Llama 4 Scout Instruct
Author: Novita AI

llama417B

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B.

Context

131K

Max output

131K

Input price

$0.18/1M tokens

Output price

$0.59/1M tokens

Capabilities

Show unsupported (4)

Reasoning & Interaction

Reasoning

Tool Calling

Infrastructure

Streaming

Fine-tuning

Details

Model IDmeta-llama/llama-4-scout-17b-16e-instruct

ProviderNovita AI

CreatorMeta Llama

Familyllama-4

Licensellama4

Statusactive

Typechat

Input modalitiestext, image

Output modalitiestext

Open weightYes

Parameters17B

Architecture—

Context window131K tokens

Max input—

Max output131K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2025-04-06

Sourceofficial

Endpoints

Chat CompletionsPOST

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

Pricing

Input

$0.18

Output

$0.59

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: llama-4

Model	Caps	Perf	Speed	Context	Max out	Pricing
Llama 4 Scout Instruct	RTSF	—	—	131K	131K	$0.18$0.59
Llama 4 Maverick Instruct	RTJJMSF	—	—	1.0M	8K	$0.27$0.85

API

GET/v1/models/novita/meta-llama/llama-4-scout-17b-16e-instruct