Back to Explore
Google: Gemini 3.5 Flash-Lite
Google·Released 2026-07-21
1.0M ctxMultimodal
Comparison data ready93% coverage16/16 fields directly observedUpdated Jul 21, 2026, 7:30 PM
About
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.
Related Models
Google: Gemini 3.6 Flash2026-07-21Google: Gemini 3.5 Flash2026-05-19Gemini 3.5 Flash (medium)2026-05-19Gemini 3.5 Flash (minimal)2026-05-19Google: Gemini 3.1 Flash Lite2026-05-07Google: Gemini 3.1 Flash Lite Preview2026-03-03Google: Gemini 3.1 Pro Preview Custom Tools2026-02-25Google: Gemini 3.1 Pro Preview2026-02-19
Pricing
Input
$0.30
per 1M tokens
Output
$2.50
per 1M tokens
Blended
$0.85
per 1M tokens
Cheaper than 43% of models. Median price is $0.69/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.85
Monthly
$25.50
vs. Similar Models
Grok 4.20 0309 (Reasoning)Q:0.0
$3.00+253%
Claude 4.5 Sonnet (Reasoning)Q:-0.1
$6.00+606%
MiMo-V2-Omni-0327Q:-0.1
$0.80-6%
OpenAI: GPT-5.1Q:+0.4
$3.44+304%
Performance
600
tokens/sec
Faster than 99% of models
9.51
seconds
Faster than 15% of models
9.51
seconds
Faster than 41% of models
Market Median
97 tok/s
520% faster
Median TTFT
1.07s
784% slower
Throughput/Dollar
705
tok/s per $/1M
Speed Comparison
LFM2.5-1.2B-Instruct
594 tok/s-1%
LFM2 1.2B
564 tok/s-6%
Granite 4.0 H Small
470 tok/s-22%
Context Window
1.0M
tokens
Larger than 88% of models
Max Output
66K
tokens
6% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
83.8%
HLE
17.5%
LiveCodeBenchNot evaluated
SciCode
40.9%
TerminalBench HardNot evaluated
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context Recall
62.0%
Tau2Not evaluated
Market AverageTop Score