Gemini 3.1 Flash Lite API Pricing and Cost Calculator
Low-latency Gemini model for high-volume multimodal and agent workloads
- Input / 1M tokens
- $0.250
- Cached input / 1M tokens
- $0.025
- Output / 1M tokens
- $1.50
- Context window
- 1.05M
Low-latency Gemini model for high-volume multimodal and agent workloads