Gemini API
ServiceGemini API is Google’s developer-facing REST/streaming interface for calling the Gemini family of large language and multimodal models. It lets engineers integrate text-, image- and chat-based Gemini completions into applications with configurable cost, latency and compatibility options.
Stories
Completed digest stories linked to this service.
-
Gemini API adds Flex and Priority inference tiers; OSS client ships circuit brea...2026-04-04Google introduced Flex and Priority inference tiers for the Gemini API to trade cost for reliability, and an O...
-
Gemini API adds OpenAI-compatible endpoint: swap three lines to try Gemini with ...2026-04-02Google added an OpenAI-compatible endpoint for Gemini, so you can call Gemini with the OpenAI SDK by changing ...
-
Ship secure Gemini apps on Vertex AI with interleaved text+image workflows2026-03-08Vertex AI anchors Gemini apps with enterprise authentication and regional controls, and developers can simplif...
-
Google debuts Gemini 3.1 Flash Lite: cheaper, faster model with variable reasoni...2026-03-04Google launched Gemini 3.1 Flash Lite, a cheaper and faster developer-focused model with variable reasoning no...
-
Google’s Gemini 3.1 Flash-Lite targets high-volume, low-latency workloads2026-03-03Google released Gemini 3.1 Flash-Lite, a faster, cheaper model aimed at high-volume developer workloads and si...
-
Google ships Gemini 3.1 Pro with big reasoning gains and 1M‑token context2026-02-20Google released Gemini 3.1 Pro with major reasoning gains, a context window up to 1 million tokens, and broad ...
-
Creator demos: Gemini 3 'Deep Think' for agent workflows2025-12-30Two creator videos claim Gemini 3 with a 'Deep Think' mode improves multi-step reasoning and enables more capa...