Google

Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite is Google’s high-efficiency multimodal model for focused subagent tasks, multi-agent workflows, reasoning, tools, and structured outputs.

gemini-3-5-flash-lite

Pricing

~71%

Input: $0.08697 / 1,000,000 tokens
Output: $0.72475 / 1,000,000 tokens
Cache read: $0.008697 / 1,000,000 tokens
Cache write: $0.024158 / 1,000,000 tokens

How pricing works

Discount history

71%Nov 8, 03:56 AM UTC

Nov 7, 11:57 PMNov 8, 03:56 AM UTC

Model details

Input: text, image, video, file, audio
Output: text
Context window: 1,000,000 tokens
Maximum output: 65,536 tokens
Availability: $4.5Uncapped capacity
Updated: 11/8/2026, 3:58:06 AM UTC

Capacity is reserved when your request is accepted.

Capabilities

ChatStreamingWeb searchVisionTool callingReasoningJSON mode

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p