domains / families / devops / agent-platform-inference

agent-platform-inference

separate

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.

When to use

• perform inference
• ask a model a question
• run a test prompt
• execute chat completions
• generate code for calling Gemini or OpenMaaS models
• authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK
• configure base URLs and global/regional endpoints
• troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors

When not to use

• deploying models to endpoints
• running model evaluations

Skill page

Source