Llama-4-Maverick-17B-128E-Instruct-FP8

Name: Llama-4-Maverick-17B-128E-Instruct-FP8
Author: DeepInfra

llama402B

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Maverick, a 17 billion parameter model with 128 experts

Context

1.0M

Max output

16K

Input price

$0.2/1M tokens

Output price

$0.8/1M tokens

Capabilities

Show unsupported (3)

Reasoning & Interaction

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Fine-tuning

Details

Model IDmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

ProviderDeepInfra

CreatorMeta Llama

FamilyLlama-4

Licensellama

Statusactive

Typechat

Input modalitiestext, image

Output modalitiestext

Open weightYes

Parameters402B

Architecture—

Context window1.0M tokens

Max input—

Max output16K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2025-04-01

Sourceofficial

Endpoints

Chat CompletionsPOST

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

Pricing

Input

$0.2

Output

$0.8

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: Llama-4

Model	Caps	Perf	Speed	Context	Max out	Pricing
Llama-4-Scout-17B-16E-Instruct	TJJMSF	—	—	328K	16K	$0.1$0.3
Llama-4-Maverick-17B-128E-Instruct-FP8	TJJMSF	—	—	1.0M	16K	$0.2$0.8

API

GET/v1/models/deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8