1
Choose prompt type
Select chat, freeform, or structured format based on your use case
2
Configure model and parameters
Pick a Gemini model, set temperature, top K/P, safety, and system instructions
3
Add multimodal inputs
Upload images, audio, video, PDFs, or code files alongside your text prompt
4
Iterate and refine
Test variations, adjust parameters, and compare responses across models
5
Export production code
Click "Get code" to generate API call snippets in Python, JavaScript, Go, Java, C#, or REST
Supported input modalities
TextPrompts, system instructions, few shot examples, and structured schemas.
ImagesPNG, JPG, GIF, WebP. Vision understanding, OCR, diagram analysis.
AudioMP3, WAV, FLAC. Transcription, analysis, and audio understanding.
VideoMP4, MOV. Scene understanding, content analysis, and summarization.
DocumentsPDFs up to 1,000 pages with full multimodal understanding.
CodeSource files in any language. Analysis, review, and generation.