Gemini 3.1 Flash Lite
Google · Low-latency Gemini model for high-volume multimodal and agent workloads
Key facts
- Provider
- Context window
- 1.0M tokens
- Max output
- 65.5K tokens
- Input price
- $0.25 / M tok
- Output price
- $1.5 / M tok
- Knowledge cutoff
- Jan 2025
- Released
- May 7, 2026
- License
- —
Capabilities
ReasoningTool callingStructured outputFile attachmentsTemperature controlOpen weights
Reasoning options
- effort minimal · low · medium · high
Pricing
USD per million tokens, list API rates.
- Input
- $0.25
- Output
- $1.5
- Cache read
- $0.025
- Cache write
- —
Modalities
- Input
- Text, Image, Video, Audio, Pdf
- Output
- Text