Some or all of the information on this page might not apply to Cloud de Confiance by S3NS. See Differences from Google Cloud for more details.

Llama 3.3 70B

Caution: As of July 21, 2026, the llama-3.3-70b-instruct-maas endpoint is deprecated and will be retired on October 21, 2026. For more information, see Open model deprecations.

Llama 3.3 70B is a text-only 70B instruction-tuned model that provides enhanced performance relative to Llama 3.1 70B and to Llama 3.2 90B when used for text-only applications.

Managed API (MaaS) specifications

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 Standard pay-as-you-go Provisioned Throughput Not supported Fixed quota
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.

Deploy as a self-deployed model

To self-deploy the model, navigate to the Llama 3.3 70B model card in the Model Garden console and click Deploy model. For more information about deploying and using partner models, see Deploy a partner model and make prediction requests.