Google Gemini

Cache content for reuse across multiple requests

Retrieve cached content details and status

List all cached content resources

Partially update cached content properties (extend TTL) — uses PATCH, not full replace

Delete a cached content resource

Generate text content from a prompt using a Gemini model

Stream generated content in real-time using Server-Sent Events

Generate embeddings for multiple items in a single synchronous call

Generate high-quality embedding vectors for text or multimodal content using Gemini embedding models

Enqueue large batches of embedding requests for cost-effective asynchronous processing

Get metadata about an uploaded file

List all uploaded files

Register Google Cloud Storage objects as Gemini files without uploading

Delete an uploaded file

Generate images using Imagen 4 models (paid account required)

List all available Gemini models

Get details about a specific Gemini model

Get status of a long-running operation (batch, video generation, etc.)

Cancel a long-running operation

List all long-running operations

Count tokens in a prompt without generating content

Generate videos using Veo models (paid account or quota required)

Create an empty file search store for document indexing and retrieval

List all file search stores

Get details of a specific file search store

Delete a file search store

Import a file from the Files API into a file search store for semantic search

List all documents in a file search store

Get details of a specific document within a file search store

Delete a specific document from a file search store