Gemini TextCompletion
CertifiedGenerate text with a Gemini model
Gemini TextCompletion
Generate text with a Gemini model
Sends a single prompt to the configured Gemini model and returns the generated text. Token usage metrics are emitted; ensure the model supports text-only input. See Gemini API about text completion for more information.
type: io.kestra.plugin.gemini.TextCompletionExamples
Text completion using the Gemini Client.
id: gemini_text_completion
namespace: company.team
tasks:
- id: text_completion
type: io.kestra.plugin.gemini.TextCompletion
apiKey: "{{ secret('GEMINI_API_KEY') }}"
model: "gemini-2.5-flash"
prompt: What color is the sky? Answer with a unique word and without any punctuation.
Properties
apiKey *Requiredstring
Gemini API key
Secret used for direct Gemini API calls; render from a secure variable.
model *Requiredstring
Generative model
Gemini model identifier to call (e.g., gemini-2.5-flash, gemini-1.5-pro). Must support the requested input type.
prompt *Requiredstring
Text prompt
Prompt string sent to the model after template rendering.
pluginDefaultsRef Non-dynamicstring
Reference (ref) of the pluginDefaults to apply to this task.
Outputs
predictions array
List of text predictions made by the model
io.kestra.plugin.gemini.AbstractGemini-Prediction
com.google.genai.types.CitationMetadata
com.google.genai.types.SafetyRating
Metrics
candidate.token.count counter
The number of candidate tokens generated by the Gemini model.
prompt.token.count counter
The number of tokens used in the input prompt.
total.token.count counter
The total number of tokens processed by the Gemini model (prompt + generated).
