Llama 3.3 70B

Llama 3.3 70B is a text-only 70B instruction-tuned model that provides enhanced performance relative to previous Llama models when used for text-only applications.

View model card in Model Garden

Supported regions
Model ID	`llama-3.3-70b-instruct-maas`
Launch stage	GA
Supported inputs & outputs	Inputs: Text, Code Outputs: Text
Capabilities	Supported Batch predictions Llama Guard Function calling Structured output Not supported
Usage types	Supported Dynamic shared quota Not supported Fixed quota Provisioned Throughput
Knowledge cutoff date	December 2023
Versions	`llama-3.3-70b-instruct-maas` Launch stage: GA Release date: April 29, 2025
	Model availability	United States `us-central1`
	ML processing	United States `Multi-region`
Quota limits	us-central1: Max output: 8,192 Context length: 128,000
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.