Google

Operational· 100% uptime, 7 days

Gemini 3.5 Flash-Lite API

The Gemini 3.5 Flash-Lite API: Google's fastest 3.5 model, 58% below list price

Price per 1M tokens58%off

Input: $0.12~~$0.30~~
Output: $1.04~~$2.50~~
Cached input: $0.012

Get your API key Try it in the playground

Model IDgemini-3.5-flash-lite

chat.py

from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="gemini-3.5-flash-lite",
    messages=[{"role": "user", "content": "Explain quicksort in two sentences."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK.

Context window: 1M tokens
Max output: 66K tokens
Input: Text, Image, Video, Audio
Output: Text
Released: Jul 21, 2026
Uptime, 7 days: 100%

Pricing

Gemini 3.5 Flash-Lite API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription and no minimum. Requests that fail are never billed.

Rate	zurelay	Google list	You save
Input per 1M tokens	$0.12	~~$0.30~~	60%off
Output per 1M tokens	$1.04	~~$2.50~~	58%off
Cached input per 1M tokens	$0.012	—	—

One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.

Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M

Output tokens per month10M

zurelay

$16.40

Google list price

$40.00

You save every month$23.60

$283.20 a year

Overview

What is Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite is the fastest and most cost-effective model in Google's Gemini 3.5 series, released on July 21, 2026. The zurelay Gemini 3.5 Flash-Lite API serves it through one OpenAI-compatible endpoint for high-volume agent steps, search and document processing, at 58% below Google's list price.

Google released Gemini 3.5 Flash-Lite on July 21, 2026, alongside Gemini 3.6 Flash. Google describes the Gemini 3.5 Flash-Lite API model as low-latency and cost-effective, built for high-throughput subagent tasks and document parsing. It reads text, images, video, audio and PDFs and writes text, with up to 1,048,576 input tokens and 65,536 output tokens. On zurelay the model ID is gemini-3.5-flash-lite, and it costs $0.12 per 1M input tokens and $1.04 per 1M output tokens.

Speed is the point. Google cites Artificial Analysis measuring it at 350 output tokens per second, the fastest model in the 3.5 series. It is also a large step up from 3.1 Flash-Lite: 54% against 31% on Terminal-Bench 2.1, 72.2% against 60.1% on the GDM-MRCR v2 long-context test, and 1140 against 642 on GDPval-AA v2. Google reports it ahead of Gemini 3 Flash on SWE-Bench Pro (54.2% against 49.6%) and OSWorld-Verified (74.0% against 65.1%).

Thinking runs at the minimal level by default, which keeps latency low. Raise it to low, medium or high when a step needs multi-step reasoning, on the same model ID. The model supports function calling and structured outputs, so it works well as a fast worker inside a larger agent. Google lists it as a stable model with no shutdown date announced, and names it as the replacement for Gemini 3.1 Flash-Lite.

Strengths

Where Gemini 3.5 Flash-Lite shines. And what teams build with it.

Built for throughput

Measured at 350 output tokens per second by Artificial Analysis, according to Google, the fastest model in the 3.5 series.

Adjustable thinking

Defaults to minimal thinking for fast answers. Raise it to low, medium or high for harder steps without switching models.

A big jump over 3.1 Flash-Lite

Google reports 54% against 31% on Terminal-Bench 2.1 and 72.2% against 60.1% on the GDM-MRCR v2 long-context test.

Long, multimodal input

Takes up to 1,048,576 tokens of text, images, video, audio or PDF in one request.

Use cases

Subagents
Hand search, lookup and tool-calling steps from a larger planner model to a fast, low-cost worker.
Document processing
Parse PDFs and long documents and extract fields into structured output.
Agentic search
Run many quick search-and-summarize loops, where per-step latency adds up.
Translation and simple data processing
Translate, clean and reformat large volumes of text with thinking left at minimal.

Get started

Call Gemini 3.5 Flash-Lite in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to zurelay.

1
Create a key
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
Get your API key
2
Point your SDK at zurelay
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1
3
Use gemini-3.5-flash-lite
Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.
gemini-3.5-flash-lite

Works with the tools you already use

Compare

Similar models. All on the same key.

58%off

Gemini 3.7 Flash

$0.32 / $1.59 per 1M tokens

Pick Gemini 3.7 Flash for harder coding, debugging and multi-step agent work where quality matters more than speed.

Gemini 3.7 Flash API

61%off

Gemini 3.1 Flash-Lite

$0.10 / $0.59 per 1M tokens

Pick Gemini 3.1 Flash-Lite for simple, high-volume jobs where its lower list price counts for more than the quality gains of 3.5.

Gemini 3.1 Flash-Lite API

57%off

MiniMax M2.7

$0.13 / $0.51 per 1M tokens

Pick MiniMax M2.7 for text-only coding and agent work on an open-weight model with a lower list output price.

MiniMax M2.7 API

FAQ

Gemini 3.5 Flash-Lite API questions.

Anything else, write to sales@zurelay.com and an engineer will answer.

How much does the Gemini 3.5 Flash-Lite API cost?

On zurelay, gemini-3.5-flash-lite costs $0.12 per 1M input tokens and $1.04 per 1M output tokens, with cached input at $0.012. Google's list price is $0.30 input and $2.50 output per 1M, so you save 58%. Thinking tokens bill as output.

Is there a cheaper Gemini 3.5 Flash-Lite API than Google's?

Yes. zurelay serves gemini-3.5-flash-lite at 58% below Google's list price, with one rate at every prompt length. You pay from prepaid credit, with no subscription.

How do I call the Gemini 3.5 Flash-Lite API with the OpenAI SDK?

Install the official openai package, set base_url to https://api.zurelay.com/v1 and use your zurelay API key. Then send a Chat Completions request with model set to "gemini-3.5-flash-lite". Messages, tools and streaming use the standard OpenAI request format.

What is the Gemini 3.5 Flash-Lite context window?

Gemini 3.5 Flash-Lite takes up to 1,048,576 input tokens and writes up to 65,536 output tokens per response. The model accepts text, image, video, audio and PDF input and writes text.

How fast is Gemini 3.5 Flash-Lite?

Google cites Artificial Analysis measuring it at 350 output tokens per second. Speed through any API also depends on load, prompt length and thinking level. The default minimal thinking level gives the fastest responses.

How is Gemini 3.5 Flash-Lite different from 3.1 Flash-Lite?

It scores much higher in Google's tests: 54% against 31% on Terminal-Bench 2.1, 72.2% against 60.1% on GDM-MRCR v2 and 1140 against 642 on GDPval-AA v2. Its list price is higher, so 3.1 Flash-Lite can still make sense for simple, very high-volume jobs.

What is Gemini 3.5 Flash-Lite best at?

Fast, high-volume work: subagent steps, agentic search, document processing and translation. With thinking raised, it also handles coding and multi-step agent tasks, where Google reports it ahead of Gemini 3 Flash on SWE-Bench Pro and OSWorld-Verified.

Does the Gemini 3.5 Flash-Lite API support streaming and rate limits?

Yes. Set stream: true, and add stream_options.include_usage to get token counts in the final chunk. Each zurelay API key can have its own monthly budget and requests-per-minute cap. Failed requests are retried on another route and never billed.

Is it the same model as Google's Gemini 3.5 Flash-Lite?

Yes, it is Google's Gemini 3.5 Flash-Lite model. Responses are sampled, so wording varies between runs, and zurelay does not promise byte-identical output. zurelay is independent and is not affiliated with or endorsed by Google.

More models on zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at zurelay, and every request costs up to 85% less from the first token.

Get your API key Talk to an engineer

Gemini 3.5 Flash-Lite API

Gemini 3.5 Flash-Lite API pricing. A fraction of the list price.

What is Gemini 3.5 Flash-Lite?

Where Gemini 3.5 Flash-Lite shines. And what teams build with it.

Built for throughput

Adjustable thinking

A big jump over 3.1 Flash-Lite

Long, multimodal input

Subagents

Document processing

Agentic search

Translation and simple data processing

Call Gemini 3.5 Flash-Lite in three steps.

Create a key

Point your SDK at zurelay

Use gemini-3.5-flash-lite