Meta: Llama 4 Maverick

Name: Meta: Llama 4 Maverick
Author: OpenRouter

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forw

Context

524K

Max output

16K

Input price

$0.19/1M tokens

Output price

$0.65/1M tokens

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Output Control

Structured Output

JSON Mode

Details

Model IDmeta-llama/llama-4-maverick

ProviderOpenRouter

Creatormeta-llama

Familyllama-4

License—

Status—

Typechat

Input modalitiestext, image

Output modalitiestext

Open weight—

Parameters—

Architecture—

Context window524K tokens

Max input—

Max output16K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2025-04-05

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.19

Output

$0.65

Cache write

—

Cache read

$0.05

Batch in

—

Batch out

—

Family Comparison: llama-4

Model	Caps	Perf	Speed	Context	Max out	Pricing
Meta: Llama 4 Scout	TJJM	—	—	1.3M	16K	$0.1$0.3
Meta: Llama 4 Maverick	TJJM	—	—	524K	16K	$0.19$0.65

API

GET/v1/models/openrouter/meta-llama/llama-4-maverick