Llama 3.1 405B

Deprecated: Llama 3.1 405B is reaching the end of its lifecycle and will be shut down on January 15, 2026.

Llama 3.1 405B is a 405b multilingual LLM optimized for multilingual dialogue use cases.

View model card in Model Garden

Model ID	llama-3.1-405b-instruct-maas
Launch stage	GA
Supported inputs & outputs	Inputs: Text, Code Outputs: Text
Capabilities	Supported Batch predictions Preview feature Llama Guard Function calling Structured output Not supported
Usage types	Supported Fixed quota Not supported Dynamic shared quota Provisioned Throughput
Knowledge cutoff date	December 2023
Versions	llama-3.1-405b-instruct-maas Launch stage: GA Release date: October 18, 2024
Supported regions
	Model availability	United States us-central1
	ML processing	United States Multi-region
Quota limits	us-central1: QPM: 60 Max output: 8,192 Context length: 128,000
Pricing	See Pricing.