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

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

llama4402B

Context

1.0M

Max output

16K

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

Creatormeta

Licensellama4

Status—

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

Function Callingfunction_calling

Call external functions and APIs

Model	Caps	Perf	Speed	Context	Max out
Llama-4-Maverick-17B-128E-Instruct-FP8	TSF	—	—	1.0M	16K
Llama-4-Maverick-17B-128E-Instruct	TSF	—	—	1.0M	16K
Llama-4-Maverick-17B-128E	TSF	—	—	1.0M	16K
Llama-4-Scout-17B-16E-Instruct	TSF	—	—	1.0M	16K
Llama-4-Scout-17B-16E	TSF	—	—	1.0M	16K

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