Gemini 3.5 Flash-Lite

Creator

Google DeepMind

Released

2026-07-21

Intelligence

36.5

Artificial Analysis Index

Coding

49.3

Artificial Analysis Index

In $/1M

$0.30

input tokens

Out $/1M

$2.50

output tokens

Blended $/1M

$0.85

3:1 blended

Speed

345

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Proprietary

non-commercial

Weights

Closed

API only

Modalities

Audio · Image · Text · Video

Parameters

Gemini 3.5 Flash-Lite is Google's low-latency, cost-effective multimodal reasoning model for high-throughput agentic workflows, document processing, data extraction, translation, and classification. It supports text, image, video, audio, and PDF inputs, a 1 million-token context window, and a 65,536-token text output.

Capability profile

Category strength across 20 domains, via LLM Stats.

legal
100finance
100agents
100reasoning
100general
100
vision
80multimodal
80code
50tool calling
50long context
20
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
84
Humanity’s Last Exam
18
MMLU-Pro
SciCode
41
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
Terminal-Bench Hard
IFBench
Via Artificial Analysis

Providers

Inference hosts serving this model — their own pricing and measured performance, cheapest input first.

ProviderIn $/1MOut $/1MThroughputLatencyStatus
Google$0.30$2.50active
All providers

1 host · via LLM Stats

© 2026 NYSGPT2525 LLC