Gemini

Use Google's Gemini Developer API to generate text, process multimodal prompts, create images, generate embeddings, count tokens, upload and manage files, inspect model metadata, and manage explicit context caches.

Supported workflows include:

• Text generation with system instructions, safety settings, structured JSON output, thinking controls, code execution, Google Search grounding, and URL Context.
• Multimodal prompts with inline data or uploaded File API references.
• Image generation through native Gemini image models and Imagen models.
• Text embeddings with single and batch inputs.
• File API upload, list, get, and delete operations.
• Cached content create, list, get, update, and delete operations.
• Model list/get metadata and token counting.

License

This integration is licensed under the FSL-1.1.