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

llama417B
Context
1.0M
Max output
16K

Capabilities

Reasoning & Interaction
Tool Calling
Infrastructure
Streaming
Fine-tuning

Details

Provider Azure AI Foundry
Creator Meta Llama
Familyllama-4
Licensellama4
Status—
Typechat
Input modalitiestext, image
Output modalitiestext
Open weightYes
Parameters17B
Architecture—
Context window1.0M tokens
Max input—
Max output16K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

API

GET/v1/models/azure/llama-4-maverick-17b-128e-instruct-fp8