Last refreshed 2026-05-11. Next refresh: weekly.
Why use PaliGemma on GCP Vertex AI?
GCP Vertex AI offers PaliGemma with free input token pricing. Vertex AI is Google Cloud's managed AI platform, offering access to Gemini models and hundreds of partner models alongside tools for fine-tuning, grounding, vector search, and end-to-end MLOps pipelines.
Input / 1M
Free
Output / 1M
Free
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install google-cloud-aiplatformAuth
export GOOGLE_CLOUD_PROJECT=...Call
import os
import vertexai
from vertexai.generative_models import GenerativeModel
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")Model ID
paligemmaRequest example
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("paligemma")
response = model.generate_content("Hello")
print(response.text)Gotchas
- 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".
- The examples expect GOOGLE_CLOUD_PROJECT; rename it only if your application config maps the new variable.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | Free |
| Output tokens | Free |
Capabilities
VisionMultimodalFunction CallingTool UseStructured Outputs
About PaliGemma
Google PaliGemma compact vision-language model for visual understanding tasks.
FAQ
What does PaliGemma cost on GCP Vertex AI?
On GCP Vertex AI, PaliGemma costs $0 per 1M input tokens and $0 per 1M output tokens.
Who created PaliGemma?
PaliGemma was created by Google DeepMind as part of the Gemma 3 model family.
Is PaliGemma open source?
PaliGemma is not open source; the seed data lists it as proprietary.
Model Specs
Released2024-03-01
ArchitectureDecoder Only