gemini-2.5-flash-lite-preview-09-2025
Low-latency Gemini model for high-volume multimodal and agent workloads
Best input price
$0.09per million tokens
- Context window
- 1,048,576
- Reasoning
- Supported
- Tool calling
- Supported
- Released
- 2026-01
tokens
Low-latency Gemini model for high-volume multimodal and agent workloads
Best input price
$0.09per million tokens
tokens