Gemini 3.5 Flash Lite (EU)

Gemini 3.5 Flash Lite EU belongs to Google’s efficiency-focused Gemini Flash Lite line, positioned around fast, economical multimodal reasoning. The supplied listing describes it as balancing multimodal input, tool use, structured output, and cost, making it suitable for focused subagents and other task-specific roles within multi-agent workflows.

The model’s large context and broad input support make it practical for workflows that combine documents, images, video, or audio with reasoning and tool calls. It is a strong fit for applications needing structured results and efficient task execution, though the available evidence does not establish parameter count, architecture, training scale, or a independently verified benchmark result.

Requestygemini-3.5-flash-lite@eugemini-flash-lite

Open provider page Provider docs

Quick Info

Provider: Requesty
Model key: gemini-3.5-flash-lite@eu
Release date: Jul 21, 2026
Last updated: Jul 21, 2026
Knowledge cutoff: 2026-03
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.33
Output token cost: $2.75

Limits

Output tokens: 65,535 tokens
Context window: 1,048,576 tokens

Transparent token rates

Compare Gemini 3.5 Flash Lite (EU) pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Gemini 3.5 Flash Lite (EU)

Requesty

Official sourceBenchmark

Requesty's documentation page for the Vertex AI EU-pinned deployment of Gemini 3.5 Flash Lite confirms the exact model identifier developers should use: vertex/gemini-3.5-flash-lite@eu, served as a managed, EU-only endpoint with no routing or failover. The page lists upstream Vertex AI rates of $0.33 per 1M input token The same page surfaces Requesty's production-side measurements of this deployment, timestamped to September 4, 2026, including a median time-to-first-token of 835ms, a p95 wait of 6.03s, and a median output throughput of 393 tokens per second, with a blended paid cost of $0.27 per 1M tokens including cache. Integration