google / text-generation API-only released 2026-07-21

Gemini 3.5 Flash Lite

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.

Input / 1M
$0.30
Output / 1M
$2.50
Context
1M
AA Intelligence
22.2
Closed weights — available only as a hosted API text + image + video + file + audio → text View on OpenRouter ↗

Pricing

via OpenRouter · USD per 1M tokens · synced 2026-10-24
$0.30
input / 1M
$2.50
output / 1M
$0.03
cached input / 1M
$2.80
1M in + 1M out
:batch variant $0.15 in · $1.25 out
Context window
1,048,576 tokens
Max output
65,536 tokens
Providers
2
Cheapest provider
Google AI Studio · $0.15 / $1.25
Best throughput
—
AA Intelligence / Coding / Agentic
22.2 / 49.3 / 14.3
✓ Tool calling ✓ Reasoning ✓ Structured outputs ✓ Image input ✓ File input ✓ Audio input ✓ Prompt caching

Price history

tracking started — chart appears after 7 days of snapshots (6 recorded)
Current: $0.30 input · $2.50 output per 1M tokens

Benchmarks

Third-party indices as published through OpenRouter — Artificial Analysis and Design Arena. Not measured by us.

AA Intelligence Index
22.2
AA Coding Index
49.3
AA Agentic Index
14.3

Providers

2 providers · per 1M tokens · last 30 min metrics
ProviderQuantContextInputOutputUptimeTok/s
Google unknown 1M $0.15 $1.25 100% —
Google AI Studio unknown 1M $0.15 $1.25 100% —
Google unknown 1M $0.30 $2.50 100% —
Google AI Studio unknown 1M $0.30 $2.50 100% —
Google unknown 1M $0.33 $2.75 100% —
Google unknown 1M $0.33 $2.75 100% —
Google unknown 1M $0.54 $4.50 100% —
Google AI Studio unknown 1M $0.54 $4.50 100% —
Provider data from OpenRouter's endpoint listing, refreshed daily.

Specifications

Organisation
google
Released on OpenRouter
2026-07-21
Context window
1,048,576 tokens
Max output
65,536 tokens
Input
text, image, video, file, audio
Output
text
Tokenizer
Gemini
Moderated by provider
No
OpenRouter id
google/gemini-3.5-flash-lite
Compare with
Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.