Llama 4 Maverick 17B 128E Instruct FP8 by Azure

Discuss

Model details

Llama 4 Maverick 17B 128E Instruct FP8

Azurellama-4-maverick-17b-128e-instruct-fp8llama

Open provider page Provider docs

Quick Info

Provider: Azure
Model key: llama-4-maverick-17b-128e-instruct-fp8
Release date: Apr 5, 2025

Cost

Input token cost: $0.25
Output token cost: $1.00

Limits

Output tokens: 16,384 tokens
Context window

Latest news about Llama 4 Maverick 17B 128E Instruct FP8

Videos about Llama 4 Maverick 17B 128E Instruct FP8

Recent tweets and retweets from Azure

Jul 1, 2026, 3:08 PMUTC

GLM 5.2, open frontier-scale intelligence on Microsoft Foundry with AMD MI300X. Running a Codex goal with an open model never felt this good! Video

Jul 15, 2026, 5:00 PMUTC

Managing PostgreSQL at scale? Discover how Azure and VS Code help teams identify issues faster, improve reliability, and optimize performance with confidence. Read the blog. msft.it/6019vFZ6Z Link Optimizing PostgreSQL on Azure directly in Visual Studio Code Learn how to…

Jul 15, 2026, 3:15 PMUTC

What’s the business value of Azure Databricks? Microsoft commissioned a Forrester Total Economic Impact™ study, and the results for a composite organization were compelling. Anavi Nahar and Jason Pereira break down the findings: msft.it/6011vFQtD

Jul 14, 2026, 6:00 PMUTC

From AI idea to MVP in 30 days. This checklist provides a clear path to building a working agent, with practical milestones you can apply immediately: msft.it/6012v0lEe

Jul 13, 2026, 4:00 PMUTC

Aurora 1.5 adds 22 more variables, hourly temporal resolution, and probabilistic ensemble forecasting to the Aurora foundation model, making it more useful for real-world weather, climate, and energy applications. Learn more: msft.it/6010v0eek Video