Gemini 3.5 Flash-Lite
by Google · google/gemini-3.5-flash-lite · #165 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
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.
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.30
per 1M tokens
Output
$2.50
per 1M tokens
Blended (3:1)
$0.85
3 input : 1 output
Cache read
$0.03
per 1M cached tokens
Cache write
$0.083
per 1M tokens
Cache & batch economics
Effective prices for Gemini 3.5 Flash-Lite with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.85 | $0.0331 | — |
| 50% | $0.749 | $0.0196 | −41% |
| 90% | $0.668 | $0.0088 | −73% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.0009 | $0.9 |
| Document summary | 8,000 | 1,000 | $0.0049 | $4.90 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.014 | $14.00 |
| Long-context analysis | 150,000 | 5,000 | $0.0575 | $57.50 |
Performance
Intelligence Index
36.5
AA composite quality
Coding Index
49.3
Math Index
—
Agentic Index
26.8
Output speed
373 tok/s
median
Time to first token
5.94s
median
Time to first answer
5.94s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 83.8% |
| Humanity's Last Exam | 17.5% |
| SciCode | 40.9% |
| AA-LCR (Long Context Reasoning) | 62.0% |
| Terminal-Bench 2.1 | 53.6% |
| τ³-Bench Banking | 16.5% |
Specs
Context window
1.05M
tokens
Max output
66K
tokens
Input modalities
text, image, video, file, audio
Tokenizer
Gemini