Skip to contentATP Token

Gemini 3.5 Flash Lite

GoogleAll Google models

Input

$0.30

USD / 1M tokens

Output

$2.50

USD / 1M tokens

Context

1.05M

tokens

Released

2026-07-21

Positioning: Economy. Price level 2 of 4 among text models. Vendor-stated speed: Fastest.

Gemini 3.5 Flash-Lite is Google's lightweight, generally available Gemini 3.5 model, released in July 2026 for high-volume, latency-sensitive work. Google describes it as its fastest and most cost-effective 3.5-class model. It defaults to minimal thinking for quick extraction and routing, and Google recommends higher thinking levels when it runs as a tool-using sub-agent.

ThinkingToolsVision
Get started freeAll model pricesCompare

Google's Gemini API model page lists a 1,048,576-token input limit and a 65,536-token output limit for Gemini 3.5 Flash-Lite.

Pricing

Pay for what you use: credits are deducted only when a request succeeds.
Prices in USD · $1 = 100 credits
Input
$0.30
Cache read
$0.03
Output
$2.50
USD / 1M tokens

Lightweight Gemini 3.5 tier for high-volume, latency-sensitive work. Passthrough of the model's official list price — no ATP markup.

Google · Family · USD / 1M tokens

Text models from the same vendor on ATP. Bars fill up to the family's highest price.
All Google models
ModelInputOutput
Gemini 3.1 Pro (Preview)gemini-3-1-pro-preview$2.00$12.00
Gemini 3.5 Flashgemini-3-5-flash$1.50$9.00
Gemini 3.6 Flashgemini-3-6-flash$1.50$7.50
Gemini 3 Flash (Preview)gemini-3-flash-preview$0.50$3.00
Gemini 3.5 Flash Lite This pagegemini-3-5-flash-lite$0.30$2.50

Cost per 1,000 typical requests

A quick estimate with fixed token counts per request. No caching, no retries. Try the estimator with your own numbers.
WorkloadUSD / 1,000
Short chat turn800 / 400$1.24
RAG answer4,000 / 500$2.45
Agent step with tools20,000 / 1,500$9.75

Where it fits

Good fit
  • High-throughput classification, routing, and JSON extraction
  • Document parsing and translation at scale, including PDFs and scanned receipts
  • Sub-agents under a larger orchestrator, with thinking raised to medium or high
  • Simple coding tasks and lightweight agentic search where latency matters
Usually not ideal
  • Complex, long-horizon coding agents — Gemini 3.6 Flash or 3.5 Flash on ATP fit better
  • Audio inputs through ATP — the catalog does not list audio for this id

Benchmarks

Vendor-reported
  • SWE-Bench Pro (Public)54.2%

    Diverse agentic coding tasks; high thinking

    Google DeepMind
  • Terminal-bench 2.154.0%

    Terminus-2 harness; high thinking

    Google DeepMind
  • OSWorld-Verified74.0%

    Agentic computer use; high thinking; averaged over 5 runs

    Google DeepMind

Scores as published by each vendor, not measured by ATP. Test conditions vary, so they are not directly comparable across vendors.

Same controls on every model: project keys, per-project model access, credit budgets, and a log of every request.Set up your organization

Cost estimator

Plug in your usage to see roughly what a month costs.
0200
0100
ESTIMATE
$8.00
USD / month
800 credits / month
  • Input$3.00
  • Output$5.00

$8.00 USD / month · 800 credits / month

An estimate at our USD prices (USD 1 = 100 credits). What each request actually cost shows up in your console's request log. Cached input is billed at the lower cache-read price, so you may spend less.

Quickstart

Keep your SDK. Point it at ATP and use a project key. Read the docs
quickstart.py · OpenAI SDK
from openai import OpenAI

client = OpenAI(
  base_url="https://api.atptoken.ai/v1",
  api_key="atp-•••"
)

r = client.chat.completions.create(
  model="gemini-3-5-flash-lite",
  messages=[{"role":"user","content":"hi"}],
)

Compare with similar models

Same type and positioning, from other vendors, closest in price first.
Compare side by side

Related models

All Google models
Gemini 3.1 Pro (Preview)gemini-3-1-pro-preview$2.00 / $12.00In / out · per 1M tokensGemini 3.5 Flashgemini-3-5-flash$1.50 / $9.00In / out · per 1M tokensGemini 3.6 Flashgemini-3-6-flash$1.50 / $7.50In / out · per 1M tokensGemini 3 Flash (Preview)gemini-3-flash-preview$0.50 / $3.00In / out · per 1M tokensNano Banana Pronano-banana-pro$0.134 / $0.1341K / 2K · per imageNano Banana Pro (Edit)nano-banana-pro-edit$0.134 / $0.1341K / 2K · per image

FAQ

4
Can Gemini 3.5 Flash Lite use tools, read images, or think before answering?
Gemini 3.5 Flash Lite supports tool calling, vision input and extended thinking, but not audio.
How much context does Gemini 3.5 Flash Lite take?
Google lists a 1,048,576-token context window for Gemini 3.5 Flash Lite. Source: Google AI for Developers — Gemini 3.5 Flash-Lite. The model list your key can see shows the limit you actually get.
Is cached input cheaper on Gemini 3.5 Flash Lite?
You pay per 1M input tokens and per 1M output tokens. Cached input costs 10% of the normal input price. You only pay when a request succeeds. $1 = 100 credits. See pricing
How do I call Gemini 3.5 Flash Lite on ATP?
Create a project API key and point any OpenAI-compatible SDK at https://api.atptoken.ai/v1. Set model to "gemini-3-5-flash-lite" (the API id, not the display name). Make sure the model is turned on for your project.

Sources

The model description on this page cites these sources. Prices come from ATP.
Get started

Start with $5. Credits never expire.

Create a project key, turn this model on, and pay only for what you use.

Get started freeTalk to enterprise