ai.google.dev

Configure Google Gemini API safety settings and handle blocked prompts/responses

Handle Google Gemini API rate limits and pick the right usage tier (RPM/TPM/RPD, 429 handling)

Run asynchronous batch jobs on the Google Gemini API for a 50% discount on non-urgent workloads

Control reasoning depth on Google Gemini thinking models with the thinking_level parameter

Generate images via the Google Gemini API — and migrate off Imagen 4 before its August 17, 2026 shutdown

Process PDFs and documents with the Google Gemini API (limits, tokenization, native text extraction)

Process PDFs and documents with the Google Gemini API (limits, tokenization, native text extraction)

Analyze images with the Google Gemini API (inline vs Files API, formats, and token cost of images)

Upload media with the Google Gemini Files API and reference it across requests (limits, expiry, when it's required)

Generate embeddings with the Google Gemini API for semantic search, classification, and clustering

Cut Google Gemini API input costs with context caching (implicit caching of repeated prompt prefixes)

Count tokens, track usage, and manage context-window limits in the Google Gemini API

Get guaranteed structured JSON output from the Google Gemini API by supplying a response schema

Use function calling / tool use with the Google Gemini API so the model can request execution of your functions in agentic workflows

Stream responses from the Google Gemini API (SSE) so text arrives incrementally instead of waiting for full generation

Generate text with the Google Gemini API (Interactions API, GA) using an API key — send prompts and read responses with usage tracking