llama3-3 (us-west1)

Meta llama3-3 hosted on GCP Vertex AI in us-west1.

Provider: All Meta models | GCP Vertex AI

Inference regions: us-west1

API Endpoint

https://us-west1-aiplatform.googleapis.com/v1/projects/{project}/locations/{region}/publishers/{publisher}/models/{model}:generateContent

Quick Start (Python)

Install: pip install google-cloud-aiplatform

import vertexai
from vertexai.generative_models import GenerativeModel

vertexai.init(project="your-project-id", location="us-west1")

model = GenerativeModel("llama3-3")

response = model.generate_content("Hello, how are you?")

print(response.text)

Supported Parameters

Parameter	Type	Description
maxOutputTokens	integer	Maximum number of tokens to generate. (≥1)
temperature	float	Controls randomness. (0–2) Default: 1.
topP	float	Nucleus sampling threshold. (0–1) Default: 1.
topK	integer	Top-K sampling. (≥0)
stopSequences	string	Sequences where generation stops.