Gemini 2.5 Flash-Lite

by Google

gemini-2-5-flash-lite

Overview

Gemini 2.5 Flash-Lite is the cheapest Gemini — lightweight, high-volume extraction and classification at the lowest rate in the lineup, with a long context window for batch work.

Quick start

Simple code & API

Create an API key, point your SDK's base URL at Kumo, and call this model with the code you already have.

Create API key

curl https://api.kumo.cloud/v1/chat/completions \
  -H "Authorization: Bearer $KUMO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2-5-flash-lite",
    "messages": [{ "role": "user", "content": "Hello from Kumo" }]
  }'

OpenAI-compatible — base URL https://api.kumo.cloud/v1. Your KUMO_API_KEY is read from the environment.