Gemini 3.1 Flash Lite Preview

gemini-3.1-flash-lite-preview

Best Input Price

$0.25 / 1M

Low-latency Gemini model for high-volume multimodal and agent workloads

Context Window

1,048,576 tokens

Reasoning

Supported

Tool Calling

Supported

Released

2026-03-03

Inference Providers (2)

Provider	Model ID	Context	Input / 1M	Output / 1M	Action
Google	gemini-3.1-flash-lite-preview	1,048,576	$0.25	$1.50	Docs ↗
Vivgrid	gemini-3.1-flash-lite-preview	1,048,576	$0.25	$1.50	Docs ↗