google/gemini-3.1-flash-lite-preview
Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Google AI Studiocache | $0.250 | $1.50 | 1.0M | 98.3% |
| Googlecache | $0.250 | $1.50 | 1.0M | 97.8% |
Gemini 3.1 Flash Lite Preview costs $0.250 per million input tokens and $1.50 per million output tokens via OpenRouter, making it 111th cheapest of 298 paid models.
Gemini 3.1 Flash Lite Preview scores 33.5 on the Artificial Analysis Intelligence Index, ranking 64th of 178 benchmarked models, with a GPQA Diamond score of 82%.
Gemini 3.1 Flash Lite Preview generates around 96 tokens per second with 624ms time-to-first-token (p50), the 71st fastest tracked model.
Gemini 3.1 Flash Lite Preview supports a 1.0M-token context window and can output up to 66K tokens. It accepts text, image, video, file, audio input.