# Google Gen AI Python SDK ## Docs - [AsyncClient](https://mintlify.wiki/googleapis/python-genai/api/async-client.md): Asynchronous client for making non-blocking requests to the Gemini API or Vertex AI API. - [batches.create](https://mintlify.wiki/googleapis/python-genai/api/batches/create.md): Create a new batch prediction job - [batches.delete](https://mintlify.wiki/googleapis/python-genai/api/batches/delete.md): Delete a batch prediction job - [batches.get](https://mintlify.wiki/googleapis/python-genai/api/batches/get.md): Retrieve information about a batch prediction job - [batches.list](https://mintlify.wiki/googleapis/python-genai/api/batches/list.md): List all batch prediction jobs - [caches.create](https://mintlify.wiki/googleapis/python-genai/api/caches/create.md): Create a cached content resource for efficient repeated queries - [caches.delete](https://mintlify.wiki/googleapis/python-genai/api/caches/delete.md): Delete a cached content resource - [caches.get](https://mintlify.wiki/googleapis/python-genai/api/caches/get.md): Retrieve cached content metadata and configuration - [caches.list](https://mintlify.wiki/googleapis/python-genai/api/caches/list.md): List all cached content resources - [caches.update](https://mintlify.wiki/googleapis/python-genai/api/caches/update.md): Update cached content expiration settings - [chats.create](https://mintlify.wiki/googleapis/python-genai/api/chats/create.md): Create a new chat session with the Gemini API - [chat.send_message](https://mintlify.wiki/googleapis/python-genai/api/chats/send-message.md): Send messages in a chat session with streaming support - [Client](https://mintlify.wiki/googleapis/python-genai/api/client.md): Synchronous client for making requests to the Gemini API or Vertex AI API. - [files.delete](https://mintlify.wiki/googleapis/python-genai/api/files/delete.md): Delete a file from the Gemini API - [files.get](https://mintlify.wiki/googleapis/python-genai/api/files/get.md): Retrieve file metadata from the Gemini API - [files.list](https://mintlify.wiki/googleapis/python-genai/api/files/list.md): List all uploaded files in the Gemini API - [files.upload](https://mintlify.wiki/googleapis/python-genai/api/files/upload.md): Upload files to the Gemini API for use in prompts - [interactions.create](https://mintlify.wiki/googleapis/python-genai/api/interactions/create.md): Create a new interaction (Beta) - [interactions.get](https://mintlify.wiki/googleapis/python-genai/api/interactions/get.md): Retrieve an interaction (Beta) - [count_tokens / compute_tokens](https://mintlify.wiki/googleapis/python-genai/api/models/count-tokens.md): Count tokens in content before API calls - [embed_content](https://mintlify.wiki/googleapis/python-genai/api/models/embed-content.md): Generate embeddings for text and multimodal content - [generate_content](https://mintlify.wiki/googleapis/python-genai/api/models/generate-content.md): Generate text and multimodal content using Gemini models - [generate_images](https://mintlify.wiki/googleapis/python-genai/api/models/generate-images.md): Generate images using Imagen models - [generate_videos](https://mintlify.wiki/googleapis/python-genai/api/models/generate-videos.md): Generate videos using Veo models - [list](https://mintlify.wiki/googleapis/python-genai/api/models/list.md): List available models - [tunings.cancel](https://mintlify.wiki/googleapis/python-genai/api/tunings/cancel.md): Cancel a running or pending tuning job - [tunings.get](https://mintlify.wiki/googleapis/python-genai/api/tunings/get.md): Retrieve information about a tuning job - [tunings.list](https://mintlify.wiki/googleapis/python-genai/api/tunings/list.md): List all tuning jobs in your project - [tunings.tune](https://mintlify.wiki/googleapis/python-genai/api/tunings/tune.md): Create a new tuning job to fine-tune a model - [Configuration Types](https://mintlify.wiki/googleapis/python-genai/api/types/config.md): Types for configuring API requests and behavior - [Content Types](https://mintlify.wiki/googleapis/python-genai/api/types/content.md): Types for representing multi-part messages and content - [Types Overview](https://mintlify.wiki/googleapis/python-genai/api/types/overview.md): Core type system for the Google Gen AI SDK - [Part Class](https://mintlify.wiki/googleapis/python-genai/api/types/part.md): Factory methods for creating content parts - [Authentication](https://mintlify.wiki/googleapis/python-genai/concepts/authentication.md): Learn how to authenticate with the Gemini Developer API and Vertex AI - [Client](https://mintlify.wiki/googleapis/python-genai/concepts/client.md): Learn how to initialize and manage the Google Gen AI client for both sync and async operations - [Models](https://mintlify.wiki/googleapis/python-genai/concepts/models.md): Learn about available Gemini models and how to select the right one for your use case - [Types](https://mintlify.wiki/googleapis/python-genai/concepts/types.md): Learn how to use Pydantic models and dictionaries for type-safe API calls - [Batch Prediction](https://mintlify.wiki/googleapis/python-genai/guides/batch-prediction.md): Process large-scale batch jobs with Vertex AI and Gemini API - [Context Caching](https://mintlify.wiki/googleapis/python-genai/guides/caching.md): Cache long prompts and content to improve performance and reduce costs - [Multi-Turn Conversations](https://mintlify.wiki/googleapis/python-genai/guides/chats.md): Create chat sessions to have multi-turn conversations with Gemini models - [Embeddings](https://mintlify.wiki/googleapis/python-genai/guides/embeddings.md): Generate embeddings for text and other content types - [Error Handling](https://mintlify.wiki/googleapis/python-genai/guides/error-handling.md): Handle API errors, configure retry logic, and implement error recovery strategies - [Files](https://mintlify.wiki/googleapis/python-genai/guides/files.md): Upload, retrieve, and delete files using the Gemini API - [Function Calling](https://mintlify.wiki/googleapis/python-genai/guides/function-calling.md): Use function calling to extend Gemini models with custom tools and actions - [Generate Content](https://mintlify.wiki/googleapis/python-genai/guides/generate-content.md): Learn how to generate text content using the Google Gen AI Python SDK with various input formats and response handling techniques. - [HTTP Options](https://mintlify.wiki/googleapis/python-genai/guides/http-options.md): Configure HTTP client settings including API version, base URL, headers, timeout, and extra body parameters - [Imagen](https://mintlify.wiki/googleapis/python-genai/guides/imagen.md): Generate, upscale, and edit images using Imagen models - [JSON Response Schema](https://mintlify.wiki/googleapis/python-genai/guides/json-response.md): Learn how to generate structured JSON outputs using JSON schemas and Pydantic models with the Google Gen AI Python SDK. - [Model Context Protocol (MCP)](https://mintlify.wiki/googleapis/python-genai/guides/mcp-support.md): Integrate MCP servers as tools for your Gemini models - [Multimodal Input](https://mintlify.wiki/googleapis/python-genai/guides/multimodal.md): Learn how to work with images, audio, video, and PDFs as input to Gemini models using the Google Gen AI Python SDK. - [Proxy Configuration](https://mintlify.wiki/googleapis/python-genai/guides/proxy.md): Configure HTTP and SOCKS5 proxies, SSL certificates, and custom authentication for the Google Gen AI SDK - [Safety Settings](https://mintlify.wiki/googleapis/python-genai/guides/safety-settings.md): Configure safety filters and handle blocked responses in Gemini models - [Streaming Responses](https://mintlify.wiki/googleapis/python-genai/guides/streaming.md): Learn how to stream content generation responses in real-time using synchronous and asynchronous streaming with the Google Gen AI Python SDK. - [System Instructions & Configuration](https://mintlify.wiki/googleapis/python-genai/guides/system-instructions.md): Learn how to configure model behavior using system instructions, temperature, max_output_tokens, and other parameters in the Google Gen AI Python SDK. - [Tokenization](https://mintlify.wiki/googleapis/python-genai/guides/tokenization.md): Count tokens, compute tokens, and use local tokenizers - [Tuning](https://mintlify.wiki/googleapis/python-genai/guides/tuning.md): Fine-tune models with Vertex AI, manage tuning jobs, and use tuned models - [Veo](https://mintlify.wiki/googleapis/python-genai/guides/veo.md): Generate videos using text-to-video, image-to-video, and video-to-video with Veo models - [Installation](https://mintlify.wiki/googleapis/python-genai/installation.md): Install the Google Gen AI Python SDK with pip or uv, including optional dependencies for enhanced performance and local tokenization. - [Introduction](https://mintlify.wiki/googleapis/python-genai/introduction.md): Build powerful AI applications with Google's Gemini models using the official Python SDK - [Quickstart](https://mintlify.wiki/googleapis/python-genai/quickstart.md): Start building awesome documentation in minutes