ai.google.dev

Accepts text prompts and multimodal content (text, code, images for Gemini 3.1 Pro) via REST endpoints at generativelanguage.googleapis.com/v1beta/models/{model}:generateContent, routing requests through Google's managed inference infrastructure with structured JSON request/response payloads. Supports six language SDKs (Python, JavaScript, Go, Java, C#) that wrap the REST layer, handling authentication via API keys and serializing multimodal content into the protocol buffer-compatible JSON format.

Implements a token-level caching mechanism where repeated prompt prefixes (e.g., system instructions, document context in RAG) are cached server-side after the first request, reducing input token costs by ~90% on subsequent requests using the same cached context. Charged at $0.20-0.40 per 1M cached input tokens (vs. $2.00 per 1M for non-cached input on Gemini 3.1 Pro) plus $4.50 per 1M tokens per hour of storage, enabling cost optimization for applications with stable, reused context.

Implements a freemium pricing model with restricted free tier (limited models, generous token limits, data used for product improvement) and pay-as-you-go paid tier ($2-18 per 1M tokens for Gemini 3.1 Pro depending on prompt length and input/output). Pricing differentiation at 200K token boundary (2-3x cost increase for longer prompts) incentivizes shorter prompts and context optimization.

Provides enterprise-grade deployment option with custom security, compliance, and SLA requirements. Includes dedicated support, provisioned throughput (guaranteed capacity), volume discounts, and access to ML Ops and Model Garden tools for advanced use cases. Exact features, pricing, and deployment options not documented; requires contacting sales.

Provides asynchronous batch processing endpoint that queues requests and processes them at lower priority, returning results via callback or polling after 24-48 hours. Reduces input and output token costs by 50% compared to real-time API calls, enabling cost-effective processing of non-urgent, high-volume inference workloads. Requests submitted as JSON arrays and results retrieved via batch job ID.

Deploys Gemini Nano model directly to Android devices (native integration) and Chrome Web Platform APIs, enabling local inference without cloud transmission. Model runs entirely on-device with zero API calls, eliminating latency, cost, and privacy concerns for supported use cases. Requires no API key and keeps all data local; trade-off is reduced capability compared to cloud Gemini models.

Integrates Google Search results into Gemini prompts, enabling models to ground responses in current web information rather than relying solely on training data. Automatically retrieves and cites relevant search results, reducing hallucination for time-sensitive queries (news, events, current prices). Charged at $14 per 1M tokens after 5,000 free prompts per month.

Enables Gemini models to plan multi-step tasks and call external functions or APIs to execute them, implementing an agent loop where the model reasons about goals, selects tools, and iterates until completion. Supports schema-based function definitions with native bindings for common APIs; exact implementation (ReAct, chain-of-thought, tool-use patterns) not documented but implied by 'agentic functions' terminology.

Provides an interactive research mode (preview feature) where Gemini breaks down research queries into sub-questions, iteratively gathers information, and presents findings with visualizations and citations. Supports MCP (Model Context Protocol) for tool integration, enabling researchers to collaborate with the model on complex investigations. Exact implementation (agentic loop, visualization engine, MCP integration) not fully documented.

Provides open-source Gemma models (weights available) that can be downloaded, fine-tuned on custom datasets, and deployed on self-managed infrastructure (on-premises, cloud, or edge). Enables full control over model behavior, data privacy, and deployment environment without vendor lock-in. Fine-tuning framework and deployment options not fully specified but implied to support standard ML workflows.

Provides native SDKs for Python, JavaScript, Go, Java, and C# that abstract the underlying REST API, handling authentication, serialization, and error handling. Each SDK exposes a consistent interface (e.g., `GenerativeModel.generate_content()`) while managing language-specific details (async/await in JS, goroutines in Go, etc.). SDKs automatically route requests to the correct API endpoint and handle response deserialization.

Provides a no-code web interface (Google AI Studio) for testing prompts, experimenting with different models, and iterating on responses before deploying to production. Enables rapid prompt engineering without writing code, with built-in model selection, parameter tuning (if available), and response comparison. Generated prompts can be exported as code snippets in supported languages.