Llama 4 Scout Instruct

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

Reasoning & Interaction
Reasoning
Tool Calling
Infrastructure
Streaming
Fine-tuning

Details

Model IDmeta-llama/llama-4-scout-17b-16e-instruct
Provider Novita AI
Creator Meta 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 date
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

ModelContextMax outPricing
Llama 4 Scout Instruct131K131K$0.18$0.59
Llama 4 Maverick Instruct1.0M8K$0.27$0.85

API

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

Llama 4 Scout Instruct

meta-llama/llama-4-scout-17b-16e-instruct

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.

Changes · 2 entries
meta-llama/llama-4-scout-17b-16e-instructcreateca7a400Nov 2, 2026, 03:02 AM
meta-llama/llama-4-scout-17b-16e-instructcreate08f0ffeMay 11, 2026, 08:27 AM