Gemini Generate Content: Google Gemini action

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Model model	options	Required	Which Gemini model to use
Prompt prompt	string	Required	Your prompt
System Instruction system_instruction	string	Optional	System-level guidance
Temperature temperature	string	Optional	0–2
Max Output Tokens max_output_tokens	string	Optional	2048
Top P top_p	string	Optional	0.95
Top K top_k	string	Optional	40

Sample request

{
  "model": "{{trigger.model}}",
  "prompt": "{{trigger.prompt}}",
  "system_instruction": "{{trigger.system_instruction}}",
  "temperature": "0.7",
  "max_output_tokens": "2048"
}

Returns

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Sample response"
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "totalTokenCount": 60,
    "promptTokenCount": 10,
    "candidatesTokenCount": 50
  }
}

Use these fields in downstream nodes for routing, logging, or error handling.

FAQ

Questions about Gemini Generate Content.

What does the Gemini Generate Content action do in Google Gemini?

Runs a multimodal completion (text, images, video, audio) against Gemini models. Supports system instruction, tools/function-calling, JSON mode, configurable safety settings. The base hook for any Gemini-based LLM workflow.

What inputs does Gemini Generate Content require?

Required: Model, Prompt. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if Google Gemini returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does Gemini Generate Content support batch operations?

Yes. Run Gemini Generate Content inside a Loop node to process arrays. Tiny Command handles Google Gemini's rate limits automatically so you don't have to throttle manually.

More actions