Gemini 3.5 Flash Lite

ModelActive

by Google · family “gemini-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. (description from the OpenRouter listing)

in: textin: imagein: videoin: filein: audioout: textReasoningTool useStructured output

Epoch Capabilities Index

145.1 #80 of 268

90% CI 142.3 – 146.7

Listing ↗

Released

21 Jul 2026

Context window

1.05M tokens

Max output

66K tokens

Input $ / 1M tokens

$0.30

Output $ / 1M tokens

$2.50

Cached input $ / 1M

$0.030

Each benchmark shown separately with its own source

Benchmark results (12)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
LMCA	agents	37.6%	57%	high	—	External ↗
DTBench	reasoning	83.5%	85%	high	—	External ↗
Mystery Game Puzzles	games	19.0% ±3.9	23%	low	5 Aug 2026	Epoch ↗
FrontierMath-Tiers-1-3-v2-Private	math	26.0% ±2.6	28%	high	2 Aug 2026	Eval log ↗
FrontierMath-Tier-4-v2-Private	math	0.0%	0%	high	2 Aug 2026	Eval log ↗
ProofBench	math	13.0%	13%	—	—	External ↗
Chess Puzzles	games	22.0% ±4.2	31%	high	6 Aug 2026	Eval log ↗
ARC-AGI-2	reasoning	10.3%	11%	high	—	External ↗
WeirdML	coding	39.0% ±0.0	42%	high	—	External ↗
OTIS Mock AIME 2024-2025	math	71.1% ±6.8	71%	high	6 Aug 2026	Eval log ↗
GPQA diamond	science	83.3% ±2.7	87%	high	6 Aug 2026	Eval log ↗
ARC-AGI	reasoning	53.5%	54%	high	—	External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

3 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.