Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite is Google DeepMind's fastest and lowest-cost model in the Gemini 2.5 family, optimized for high-throughput, latency-sensitive tasks such as classification, extraction, summarization, and routing. It supports multimodal inputs (text, image, video, audio, PDF) with a 1M-token context window and includes thinking controls, Grounding with Google Search, and code execution. Source: supabase.