Gemini 2.0 Flash-Lite
Google DeepMindMost cost-efficient Gemini model. Great throughput for high-volume applications.
Context window1000K tokens
Input / 1M tokens$0.075
Output / 1M tokens$0.3
Version History
gemini-2.0-flash-lite-001majorFebruary 5, 2025
Gemini 2.0 Flash-Lite reaches GA as the most cost-efficient Gemini model. Replaces 1.5 Flash for high-volume workloads.