Gemini 2.5 Flash Lite
JSON →A lightweight and cost-efficient variant of Gemini 2.5 Flash, optimized for high-throughput and latency-sensitive multimodal tasks.
Specs
context window 1.0M tokens
max output 66K tokens
input price $0.1 / 1M tokens
output price $0.4 / 1M tokens
Capabilities
streamingvisiontool-usejson-modefunction-callingprompt-cachingreasoning
Dates
releasedApr 2025
Resources
API
full doc /v1/models/gemini-2.5-flash-lite