Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite is our fastest, most cost-efficient multimodal model, optimized for ultra-low latency and high-throughput tasks.

This model is the premier choice for high-volume, cost-sensitive applications: it delivers best-in-class speed and is priced aggressively at $0.10 per 1M input tokens. Gemini 2.5 Flash-Lite supports a massive 1-million-token context window and handles multimodal inputs (text, audio, images, video, PDF). Developers can leverage native capabilities like Function Calling, Code Execution, and Google Search Grounding. For complex tasks, activate 'Thinking mode' with a budget (512–24,576 tokens) to selectively trade speed for enhanced reasoning and accuracy.

https://ai.google.dev/models/gemini