Gemini 3.5 Flash Lite
by Vercel AI Gateway · family gemini-flash-lite · listed Jul 2026RTV
Low-latency Gemini model for high-volume multimodal and agent workloads
Current rates USD per 1M tokens
Input$0.30
Output$2.50
Cache read$0.03
Cache write—
Against the market
On the record
- Model id
google/gemini-3.5-flash-lite- Context window
- 1M tokens
- Max output
- 65K tokens
- Input modalities
- text, image, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Mar 2026
- Released
- 2026-07-21
- Last updated
- 2026-07-21
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.15 in · $1.25 out
- NanoGPT$0.30 in · $2.50 out
- Impossibl$0.30 in · $2.50 out
- LLM Gateway$0.30 in · $2.50 out
- OrcaRouter$0.30 in · $2.50 out
- Vertex$0.30 in · $2.50 out
- Pioneer$0.30 in · $2.50 out
- Requesty$0.30 in · $2.50 out
- CrossModel$0.30 in · $2.50 out
- Google$0.30 in · $2.50 out
- DevPass (LLM Gateway)$0.30 in · $2.50 out
- Opper$0.30 in · $2.50 out
- Merge Gateway$0.30 in · $2.50 out
- Abacus$0.30 in · $2.50 out
- OpenCode Zen$0.30 in · $2.50 out