Skip to main content
Use the full image model ID:
Do not shorten it to gemini-3.1-flash-lite; that identifies the text model.

Output controls

This API exposes these ten explicit ratios for Lite:
Google’s current model page says the model supports fourteen ratios but explicitly lists the same ten values above. YingTu documents the explicit values available in its current model-fixed form rather than guessing the other four.

Generation body

Reference-image input

Add one or more source images after the instruction:
Unified asynchronous editing accepts 1–16 images, with a 20 MiB decoded limit per file and 64 MiB total. Synchronous multi-image behavior follows the current official Gemini model contract. A fixed maximum source-image byte or pixel size is not currently published. Total request-body, proxy, and upstream limits may differ; reduce the source image after HTTP 413, and contact API support before relying on a guaranteed production envelope.

Copy Lite examples

Run complete generation, asynchronous, editing, and parsing flows.

Compare the family

Choose Flash before the integration needs a higher output tier.
Last modified on September 3, 2026