All skills
agent-platform-deploy
Deploy a Model Garden model to an Agent Platform endpoint, then check status or undeploy it.
- Part of google/skills
- 10.3k installs
- Machine Learning · Model serving
When to use it
You have a model picked out and a project ready, but still need it running on an endpoint with the right machine type and cost estimate.
For example
You say
Use agent-platform-deploy to deploy a Gemma model from Model Garden to a new endpoint in us-central1 on g2-standard-24, and show me the hourly cost first.
You get
- Deploy command with cost estimate
- Endpoint display name
- Operation name for status checks
How it works
- Presents a confirmation card with the exact command, hardware, and hourly cost before deploying.
- Checks the live catalog instead of naming model versions from memory.
- Suggests an alternative region when quota or capacity blocks the deploy.
Before installing
Needs an authenticated gcloud CLI with the project and region set; some Hugging Face models also need a Hugging Face access token.
This skill includes 2 scripts your assistant may run on your computer.
More Model serving skills
See all- serving-llms-vllm66Serves large language models at high throughput with an OpenAI-compatible API and quantization.
- omh-inference-serving31Helps choose a serving engine and set up self-hosted LLM serving on GPUs.
- tensorrt-llm21Runs high-throughput language model inference on NVIDIA GPUs.
- perf-optimization18Routes performance work to the right specialist and applies optimizations or kernels in a safe order.
Also in this pack
- cloud-run-basics19.4kDeploys and manages Cloud Run services, jobs and worker pools.
- gemini-api18.8kWrites code that calls Gemini models for text, images, video, audio, embeddings and more across languages.
- google-cloud-recipe-auth17.1kExplains how to authenticate and authorize users and services to Google Cloud APIs, including IAM and ADC.
- google-cloud-recipe-onboarding16.9kWalks a new developer through creating a Google Cloud account, setting up billing and deploying a first resource.