Tag archive
Google shipped Gemini 3.8 Flash TTS and Flash-Lite TTS today, with the docs and pricing page updated same-day. Includes a working code example using the new speech_metadata prompting shape, benchmark results, and real per-token pricing versus the outgoing preview model.
gemini-omni-flash-preview shuts down 30 Sept 2026, gemini-2.5-flash-image on 2 Oct. Replacement IDs, behaviour differences to test, and an inventory script.
LLM API 과금 폭탄 막는 법: 일일 상한과 선불 크레딧 관리 경험기 안녕하세요, 코딩아빠입니다. 오늘은 제가 LLM API를 사용하면서 겪었던 일과 그...
Imagen 4 shuts down 17 August 2026: the generate_content() migration, with cost...
Compare Claude, GPT-4o, and Gemini 2.5 API pricing for 2026. Token costs, context window economics, and a free calculator to estimate your monthly AI spend.
At Pixel Office, we proudly launched our latest lead magnet, the "AI Voice Agent Playground," allowing businesses to experience the power of AI voice assistants. Dive with us into the technical details and team collaboration behind this innovative tool.
Google Veo 3.1 Lite: AI video with native audio via Gemini API at under half the cost of Veo 3.1 Fast. Dev guide: features, pricing, and code examples.
Developers utilizing Google Gemini's generateContentStream for real-time conversational AI...
Google Gemini 3.1 Ultra ships the largest publicly available context window at 2M tokens. Complete developer guide: real use cases, cost math, and API code.
Google DeepMind released Gemini 3.7 Flash on August 13, 2026. The model builds on Gemini 3.6 Flash with algorithmic improvements aimed at software engineering, web development, knowledge work, and agentic workflows—while launching at an introductory $0.75/$3.75 per-million-token price.
Achieving Precision in Gemini API Video Analysis: Solving Time Drift for Your Google File...
The Challenge: Gemini API's Long Audio Transcription Glitches A significant challenge has...