GoogleGemini 3
Gemini 3.1 Flash-Lite
Gemini 3.1 Flash-Lite is an available stable API for efficient multimodal processing.
What the release provides
Google lists translation, transcription, extraction and routing among its intended uses. It accepts text, image, video, audio and PDFs, returns text, and supports thinking.Gemini 3.1 Flash-Lite official API documentation
How to use it well
Practical guidance. Use a clear output contract for routing or extraction. Review rare categories and ambiguous documents separately from common inputs. For a router, measure the downstream result of each decision, since one incorrect route can cost more than the initial request.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | gemini-3.1-flash-lite |
| Context window | 1,048,576 tokens API input limit; reserve output capacity where the service shares one window. Gemini 3.1 Flash-Lite official API documentation |
| Maximum output | 65,536 tokens Published API output limit; request settings can be lower. Gemini 3.1 Flash-Lite official API documentation |