Gemini 3.1 Flash-Lite

Google's lightweight multimodal model is designed for translation, transcription and information extraction at scale. It can produce structured JSON from documents or messages and apply additional reasoning to more involved requests.

CONTEXT1M

MAX OUTPUT64K

LAST SCAN13 Nov 2026

Reasoning TextImageAudio

Free aggregator routes

These are the aggregator routes recorded in the current or last published catalog. Each route keeps its exact model ID and thinking information.

Google advertises free-tier input and output for the stable model. Quotas and eligibility apply; no successful account-access test is supplied.

Limits above: Google AI Studio. Available gateway routes are listed below.

Google AI Studio

Info

Thinking: Supported
Effort levels: minimal · low · medium · high
Control: Always enabled
Default: Enabled

Model ID · Google AI Studio APIgemini-3.1-flash-lite

Use it through LiteLLM

Import the current LiteLLM-compatible YAML and use the exact model ID shown above. The catalog is generated from the same reviewed scan data as the download.

Download LiteLLM YAML

Sources & references

Google Gemini 3.1 Flash-Lite specifications and developer guide