gemini-3.5-flash-lite

Common Name: Gemini 3.5 Flash-Lite

-10%On SaleReleased on Jul 21 12:00 AMKnowledge Cutoff Mar 1 12:00 AMSupportedTool InvocationSupportedReasoning

Google's fastest, most cost-effective Gemini 3.5 model, delivering 350 output tokens/sec for high-throughput tasks like agentic search, document processing, and translation.

Specifications

Context

1000K

Maximum Output

64K

Inputtext, image, audio, video

Outputtext

Performance (7-day Average)

Collecting…

Availability Trend (24h)

Pricing

Input$0.27/MTokens

Cached Input$0.027/MTokens

Output$2.25/MTokens

Thinking Output$2.25/MTokens

Performance Metrics (24h)

Similar Models

Gemini 3 Flash Preview

$0.45/$2.70/M-10%

ctx1.0Mmax64Kavail—tps—

InOutCap

RankedInstruction#3

Preview of Google's next-generation Gemini 3 Flash model, optimized for speed with frontier intelligence combined with superior search and grounding capabilities.

Gemini 3.1 Flash-Lite

$0.225/$1.35/M-10%

ctx1.0Mmax64Kavail—tps—

InOutCap

RankedInstruction#5

Google's most cost-efficient Gemini 3 series model, optimized for high-volume agentic tasks, translation, and simple data processing with 2.5X faster time to first token than 2.5 Flash.

Gemini 3.1 Flash Image

$0.45/$2.70/M-10%

ctx1.0Mmax64Kavail—tps—

InOutCap

Gemini 3.1 Flash Image generation model designed for speed and efficiency, effective for quick interactive image responses and high throughput.

Gemini 2.5 Flash Image

$0.27/$2.25/M-10%

ctx128Kmax8Kavail—tps—

InOutCap

Gemini 2.5 Flash Image generation model on Vertex AI, producing native image output alongside text understanding.