GoogleGemini​Google​Gemini

Google Gemini Model Provider

WARNING: when using tools, this provider didn't support JSON Schema with anyOf.

yaml
type: "io.kestra.plugin.ai.provider.GoogleGemini"

Chat completion with Google Gemini

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      apiKey: "{{ kv('GOOGLE_API_KEY') }}"
      modelName: gemini-2.5-flash
      thinkingEnabled: true
      thinkingBudgetTokens: 1024
      returnThinking: true
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{inputs.prompt}}"

Chat completion with Google Gemini with a local base URL + PEM certificates

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      apiKey: "{{ kv('GOOGLE_API_KEY') }}"
      modelName: gemini-2.5-flash
      clientPem: "{{ kv('CLIENT_PEM') }}"
      caPem: "{{ kv('CA_PEM') }}"
      baseUrl: "https://internal.gemini.company.com/endpoint"
      thinkingEnabled: true
      thinkingBudgetTokens: 1024
      returnThinking: true
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{inputs.prompt}}"
Properties

API Key

Model name

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.