Vercel AI Gateway
Gemini 3.5 Flash Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
google/gemini-3.5-flash-liteContext
1M
Max output
65K
Input $/M
$0.30
Output $/M
$2.50
Cache read $/M
$0.03
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 88% of the 5,751 models listed
Input price$0.30
Cheaper than 56% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentssupported
Temperaturesupported
Open weightsnot supported
Interleaved thinkingnot supported
Modalities
Input
TextImagePDF
Output
Text
Reasoning controls
effortminimal, low, medium, highPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.30 |
| Output | $2.50 |
| Cache read | $0.03 |