Using PaLM 2 (text-bison) on Google Vertex AI on GCP Vertex AI

Implementation guide · Palm 2 · Google DeepMind

Serverless

GCP Vertex AI exposes PaLM 2 (text-bison) on Google Vertex AI through model ID vertex-palm-2-text-bison. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-15. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at GCP Vertex AI and generate an API key.
  2. 2
    Use the GCP Vertex AI SDK or REST API to call vertex-palm-2-text-bison — see the documentation for request format.
  3. 3
    You'll be billed $0.13/1M input, $0.38/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

Install
pip install google-cloud-aiplatform
API key
GOOGLE_CLOUD_PROJECT
Model ID
vertex-palm-2-text-bison

For Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".

import os
import vertexai
from vertexai.generative_models import GenerativeModel

# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("vertex-palm-2-text-bison")
response = model.generate_content("Hello")
print(response.text)

Pricing on GCP Vertex AI

TypePrice (per 1M)
Input tokens$0.13
Output tokens$0.38

Capabilities

Structured Outputs

About PaLM 2 (text-bison) on Google Vertex AI

PaLM 2 (text-bison) on Google Vertex AI is Google DeepMind's Palm 2 model. It offers an 8K-token context window.

Full model details →

Model Specs

Released2023-12-06
Context8k
ArchitectureDecoder Only

More Models on GCP Vertex AI

Chat BisonText BisonPaLM 2 (chat-bison) on Google Vertex AI
All models on GCP Vertex AI →

Provider

GCP Vertex AI

Google Cloud Platform (GCP)

Mountain View, California, United States