Gemini 3.1 Flash Lite Preview

JSON →
google llm
text

A lightweight preview of Google's Gemini 3.1 Flash model, optimized for cost-efficient and fast inference.

context window 1.0M tokens
max output 66K tokens
input price $0.25 / 1M tokens
output price $1.5 / 1M tokens
streamingprompt-cachingfunction-callingtool-usevisionreasoningjson-mode