/embedded-gemini | Type: Embedded | PCID required: No
Generate text using Google Gemini models. Supports multimodal analysis including images, video, audio, and documents.
Tools
| Tool | Description |
|---|---|
embedded-gemini_generate | Generate text using Gemini |
embedded-gemini_generate
Generate text using a Google Gemini model. Supports multimodal analysis including images, video, audio, and documents. Parameters:| Parameter | Type | Required | Description |
|---|---|---|---|
model | enum | No | Model to use: gemini-3-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash. Default gemini-2.5-flash |
systemPrompt | string | No | System prompt to guide model behavior |
userPrompt | string | Yes | User prompt or question |
fileUrls | string[] | No | URLs of files to analyze. Supported formats: images (.jpg, .jpeg, .png, .webp), videos (.mp4, .webm, .mkv, .mov), documents (.pdf, .txt), audio (.mp3, .wav, .webm, .m4a, .opus, .aac, .flac) |
| Field | Type | Description |
|---|---|---|
output | string or object | Generated text or structured output |
metadata | object | Response metadata |
metadata.model | string | Model used for generation |
metadata.usage | object | Token usage statistics |
metadata.usage.promptTokens | number | Number of input tokens |
metadata.usage.completionTokens | number | Number of output tokens |
metadata.usage.totalTokens | number | Total tokens used |
| Model | Description |
|---|---|
gemini-3-pro-preview | Multimodal support, large context, advanced reasoning |
gemini-3-flash-preview | Fast and cost-efficient with multimodal support |
gemini-2.5-pro | Enhanced thinking and reasoning, advanced coding |
gemini-2.5-flash | Cost-efficient, supports higher token limits (default) |
gemini-2.0-flash | Next generation speed, thinking, realtime streaming |