---
last_updated: 2026-11-20
source_url: https://opper.ai/google/gemini-3-5-flash-lite
title: "Gemini 3.5 Flash-Lite by Google"
description: "Gemini 3.5 Flash Lite is Google's low-latency workhorse for high-volume automation, pairing 1M context with audio, video, and PDF understanding."
---

# Gemini 3.5 Flash-Lite

By [Google](https://opper.ai/google).

Released 21 Jul 2026 · [Announcement](https://ai.google.dev/gemini-api/docs/deprecations) · [All Google releases](https://opper.ai/model-releases/google)

Gemini 3.5 Flash Lite is Google's speed-focused small model, launched on July 21, 2026 alongside Gemini 3.6 Flash and delivering a substantial quality jump over the previous Flash Lite generation from March. Despite the lite label it retains a 1 million token context window, a 65K output ceiling, and full multimodal input spanning images, audio, video, and PDFs.

The model is designed for high-throughput, low-latency workloads such as agentic search, document processing, and bulk automation. Tool calling and structured output make it a natural subagent inside larger agent systems, handling the high-frequency steps while heavier models are reserved for the hard decisions.

## Available routes

Gemini 3.5 Flash-Lite runs on 5 different routes through the Opper gateway. Prices are per 1M tokens. Zero data retention on Google Cloud is available on Enterprise. In the EU it is served by Google Cloud. [See every Gemini model hosted in the EU](https://opper.ai/models/eu/gemini). Some routes also sell flex and priority processing: the same model at another price, picked per request with service_tier. [How service tiers work](https://docs.opper.ai/build/gateway/service-tiers). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=gemini-3.5-flash-lite.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Google Cloud](https://opper.ai/provider/google) | `gemini/gemini-3.5-flash-lite` | US (United States) | Abuse monitoring | No | $0.30 | $2.50 | $0.03 ($0.38 write) |
| [Google Cloud](https://opper.ai/provider/google), Flex | `gemini:flex/gemini-3.5-flash-lite` | US (United States) | Abuse monitoring | No | $0.15 | $1.25 | $0.02 |
| [Google Cloud](https://opper.ai/provider/google), Priority | `gemini:priority/gemini-3.5-flash-lite` | US (United States) | Abuse monitoring | No | $0.54 | $4.50 | $0.05 |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai-zdr/gemini-3.5-flash-lite` | Multi-region | Yes, on Enterprise | No | $0.30 | $2.50 | $0.03 |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai-zdr/gemini-3.5-flash-lite-eu` | EU | Yes, on Enterprise | No | $0.30 | $2.50 | $0.03 |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai/gemini-3.5-flash-lite` | Multi-region | Abuse monitoring | No | $0.30 | $2.50 | $0.03 ($0.38 write) |
| [Google Cloud](https://opper.ai/provider/google), Flex | `vertexai:global:flex/gemini-3.5-flash-lite` | Multi-region | Abuse monitoring | No | $0.15 | $1.25 | $0.01 |
| [Google Cloud](https://opper.ai/provider/google), Priority | `vertexai:global:priority/gemini-3.5-flash-lite` | Multi-region | Abuse monitoring | No | $0.54 | $4.50 | $0.05 |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai/gemini-3.5-flash-lite-eu` | EU | Abuse monitoring | No | $0.33 | $2.75 | $0.03 ($0.41 write) |
| [Google Cloud](https://opper.ai/provider/google), Priority | `vertexai:eu:priority/gemini-3.5-flash-lite` | EU | Abuse monitoring | No | $0.59 | $4.95 | $0.06 |

## Key info

- Model id: `gemini-3.5-flash-lite` (routes across Google Cloud)
- Input: Text, Image, Audio, Video, Files
- Output: Text
- Features: Tools, Structured output, PDF input
- Context window: 1M
- Max output: 66K
- Input price: $0.30 per 1M tokens ($0.03 cache read · $0.38 write)
- Output price: $2.50 per 1M tokens
- Released: 21 Jul 2026
- EU residency available on Google Cloud
- US residency available on Google Cloud
- Zero data retention with abuse monitoring
- Zero data retention on Enterprise
- No training by default

## Data handling per route

Each route hosting Gemini 3.5 Flash-Lite has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### Google Cloud — United States

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs.

- Zero data retention: With abuse monitoring, window not stated.
- Training: No training on customer data.
- Logging: Abuse monitoring
- Abuse monitoring: On by default, holds flagged content, 55 days, a person can view samples
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-17.

### Google Cloud — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. Available under a signed Enterprise agreement. No training on customer data. GLOBAL; SCCs.

- Zero data retention: Yes, on Enterprise. Nothing is logged, held for abuse monitoring or used for training.
- Plan: Signed Enterprise agreement
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, keeps nothing
- Caching: Content cached for replay
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-02.

### Google Cloud — EU

Zero data retention: nothing is logged, held for abuse monitoring or used for training. Available under a signed Enterprise agreement. No training on customer data. EU.

- Zero data retention: Yes, on Enterprise. Nothing is logged, held for abuse monitoring or used for training.
- Plan: Signed Enterprise agreement
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, keeps nothing
- Caching: Content cached for replay
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-09-02.

### Google Cloud — Multi-region

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. GLOBAL; SCCs.

- Zero data retention: With abuse monitoring, flagged content held.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-26.

### Google Cloud — EU

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. EU.

- Zero data retention: With abuse monitoring, flagged content held.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-10-26.

## Best for

Where Gemini 3.5 Flash-Lite ranks among the models on Opper with a score for each use case (0 to 100).

- [Coding](https://opper.ai/models?use=coding): 4.0 (FrontierCode 2.0 and Terminal-Bench 4.0)
- [Legal](https://opper.ai/models?use=legal): 23.9 (Legal tasks and reasoning)
- [Healthcare](https://opper.ai/models?use=healthcare): 20.5 (Healthcare and medical)
- [Finance](https://opper.ai/models?use=finance): 23.3 (Finance and accounting)
- [Agents](https://opper.ai/models?use=agents): 13.0 (Terminal-Bench 4.0 and AutomationBench)

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/gemini-3-5-flash-lite)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #63 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Output speed: 409 tok/s
- Intelligence Index: 11.7

### Coding

- FrontierCode 2.0: 6%
- Terminal-Bench 4.0: 1%
- SciCode: 41%

### Agentic & knowledge work

- AutomationBench: 25%
- GDPval: 25%
- GDP.pdf: 14%
- Briefcase (Elo): 652

### Science & reasoning

- Terminal-Bench Science: 0%
- CritPt (hard): 4%
- HLE Diamond: 10%
- Humanity's Last Exam: 19%
- GPQA Diamond: 84%
- Long-context reasoning: 76%

### Knowledge

- Omniscience: 6.9
- MMMU-Pro: 79%

### By domain

- Finance & accounting: 23.3
- Legal: 23.9
- Healthcare & medical: 20.5
- Engineering: 21.2
- Economics: 21.9
- Strategy & operations: 20.7

## Get started

Call Gemini 3.5 Flash-Lite through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Gemini 3.5 Flash-Lite is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Gemini 3.5 Flash-Lite
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "gemini-3.5-flash-lite",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "gemini-3.5-flash-lite",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "gemini-3.5-flash-lite",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash-lite",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Gemini 3.5 Flash-Lite in your apps

Pick your tool to see how to run it on Gemini 3.5 Flash-Lite through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/gemini-3-5-flash-lite)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/gemini-3-5-flash-lite)
- [Codex](https://opper.ai/apps/codex/gemini-3-5-flash-lite)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/gemini-3-5-flash-lite)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/gemini-3-5-flash-lite)
- [Aider](https://opper.ai/apps/aider/gemini-3-5-flash-lite)
- [Goose](https://opper.ai/apps/goose/gemini-3-5-flash-lite)
- [Droid](https://opper.ai/apps/droid/gemini-3-5-flash-lite)
- [OpenCode](https://opper.ai/apps/opencode/gemini-3-5-flash-lite)
- [Pi](https://opper.ai/apps/pi/gemini-3-5-flash-lite)
- [OpenClaw](https://opper.ai/apps/openclaw/gemini-3-5-flash-lite)
- [Hermes](https://opper.ai/apps/hermes/gemini-3-5-flash-lite)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/gemini-3-5-flash-lite)
- [OmniRoute](https://opper.ai/apps/omniroute/gemini-3-5-flash-lite)
- [Cursor](https://opper.ai/apps/cursor/gemini-3-5-flash-lite)
- [Cline](https://opper.ai/apps/cline/gemini-3-5-flash-lite)
- [Continue](https://opper.ai/apps/continue/gemini-3-5-flash-lite)
- [Kilo Code](https://opper.ai/apps/kilo-code/gemini-3-5-flash-lite)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/gemini-3-5-flash-lite)
- [Zed](https://opper.ai/apps/zed/gemini-3-5-flash-lite)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/gemini-3-5-flash-lite)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/gemini-3-5-flash-lite)
- [n8n](https://opper.ai/apps/n8n/gemini-3-5-flash-lite)
- [LibreChat](https://opper.ai/apps/librechat/gemini-3-5-flash-lite)
- [Open WebUI](https://opper.ai/apps/open-webui/gemini-3-5-flash-lite)
- [See all apps](https://opper.ai/apps)

## Other models from Google

- [Gemini 4 Argon](https://opper.ai/google/gemini-4-argon)
- [Gemini 3.8 Flash](https://opper.ai/google/gemini-3-8-flash)
- [Gemini 3.7 Flash](https://opper.ai/google/gemini-3-7-flash)
- [Gemini 3.6 Flash](https://opper.ai/google/gemini-3-6-flash)
- [Gemini 3.5 Flash](https://opper.ai/google/gemini-3-5-flash)
- [Gemini 3.1 Pro Preview](https://opper.ai/google/gemini-3-1-pro-preview)
