AI TOOLS RADAR
Submit
All models / GOOGLE
google logo
google

Google: Gemini 3.5 Flash Lite

Source description (English)

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

View source on OpenRouter
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
65,536 tokens
Architecture
text+image+file+audio+video->text
Tokenizer
Gemini
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.3
per 1M tokens
Output
$2.5
per 1M tokens
Cache read
$0.03
per 1M tokens
Cache write
$0.0833
per 1M tokens
Image input
$0.3
per 1M tokens
Audio input
$0.3
per 1M tokens
Input Audio Cache
$0.03
per 1M tokens
Web search
$14
per 1,000 calls
API

Model configuration

Reasoning

Reasoning required
Yes
Default parameters
minimal
Capabilities
high, medium, low, minimal
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3.5-flash-lite","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagevideofileaudio
Output
text
Reasoning

Yes · high · medium · low · minimal

API

Supported API parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Available providers

8 providers

Checked: September 7, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Google

Not provided
Context
1.0M
Maximum output
66K
Input
$0.15
Output
$1.25
Cache read
$0.015
Cache write
$0.0417

Google AI Studio

Not provided
Context
1.0M
Maximum output
66K
Input
$0.15
Output
$1.25
Cache read
$0.015
Cache write
$0.0417

Google AI Studio

Not provided
Context
1.0M
Maximum output
66K
Input
$0.3
Output
$2.5
Cache read
$0.03
Cache write
$0.0833

Google

Not provided
Context
1.0M
Maximum output
66K
Input
$0.3
Output
$2.5
Cache read
$0.03
Cache write
$0.0833

Google

Not provided
Context
1.0M
Maximum output
66K
Input
$0.33
Output
$2.75
Cache read
$0.033
Cache write
$0.0833

Google

Not provided
Context
1.0M
Maximum output
66K
Input
$0.33
Output
$2.75
Cache read
$0.033
Cache write
$0.0833

Google

Not provided
Context
1.0M
Maximum output
66K
Input
$0.54
Output
$4.5
Cache read
$0.054
Cache write
$0.15

Google AI Studio

Not provided
Context
1.0M
Maximum output
66K
Input
$0.54
Output
$4.5
Cache read
$0.054
Cache write
$0.15
google

4 models

All models
google logogoogle

Google: Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Context
1.0M
Input
text · image · video · file · audio
Output
text
Input: $0.75Output: $3.75per 1M tokens
View model details →
google logogoogle

Google: Gemini 3.8 Flash (batch)

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Context
1.0M
Input
text · image · video · file · audio
Output
text
Input: $0.375Output: $1.875per 1M tokens
View model details →
google logogoogle

Google: Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

Context
1.0M
Input
text · image · video · file · audio
Output
text
Input: $0.75Output: $3.75per 1M tokens
View model details →
google logogoogle

Google: Gemini 3.7 Flash (batch)

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

Context
1.0M
Input
text · image · video · file · audio
Output
text
Input: $0.375Output: $1.875per 1M tokens
View model details →