Skip to main content

Llama 4 Maverick 17B-128E

Llama 4 Maverick 17B-128E is Llama 4's largest and most capable model. It uses the Mixture-of-Experts (MoE) architecture and early fusion to provide coding, reasoning, and image capabilities.

Try in Vertex AI View model card in Model Garden

Supported regions
Model ID	`llama-4-maverick-17b-128e-instruct-maas`
Launch stage	GA
Supported inputs & outputs	Inputs: Text, Code, Images Outputs: Text
Capabilities	Supported Batch predictions Function calling Structured output Not supported Llama Guard
Usage types	Supported Dynamic shared quota Not supported Fixed quota Provisioned Throughput
Knowledge cutoff date	August 2024
Versions	`llama-4-maverick-17b-128e-instruct-maas` Launch stage: GA Release date: April 29, 2025
	Model availability	United States `us-east5`
	ML processing	United States `Multi-region`
Quota limits	us-east5: Max output: 8,192 Context length: 524,288
Pricing	See Pricing.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025年11月07日 UTC.