Google · in Borg

Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite is the economical counterpart to 3.5 Flash, intended for quick, high-volume subagent tasks rather than lengthy deliberation.

Reasoning1,048,576 tokenstext, image, video, audio, pdf

1,048,576 tokensContext window

1572 msMedian time to first token (gateway proxy)

59.2Output tokens per second (whole turn)

100%Request success

$0.3 / $2.5Vendor API price in / out · per 1M

Included in Borg

Download Borg Borg for Business

At a glance

Specification	Value
Provider	Google
Family	Gemini
Release date	2026-07-21 Vendor source
Context window	1,048,576 tokens Vendor source
Input modalities	text, image, video, audio, pdf
Output modalities	text
Reasoning	Yes
Open weights	No
Borg lane ids	`antigravity/gemini-3.5-flash-lite`, `google/gemini-3.5-flash-lite`
Versions in Borg	Gemini 2.5 Flash-Lite · Gemini 3.1 Flash-Lite · Gemini 3.5 Flash-Lite
Median time to first token (gateway proxy) on Borg	1572 ms
Median tokens per second (end to end) on Borg	59.2 output tokens per second

Not published by the vendor: thinking modes, knowledge cutoff, fusion roles.

What Gemini 3.5 Flash-Lite is good for

Gemini 3.5 Flash-Lite is the economical counterpart to 3.5 Flash, intended for quick, high-volume subagent tasks rather than lengthy deliberation. It can read images, video, audio and PDFs along with text and is positioned for document parsing, translation and extraction where many requests must finish promptly. Compared with 3.1 Flash-Lite, it is a newer Lite revision; compared with full 3.5 Flash, it prioritizes throughput and a much lower API token rate over sustained frontier-level agent work. Thinking and tool calling remain available, but it still outputs text rather than images. Borg includes Flash-Lite in the subscription; Borg Fusion may pick it for repetitive lightweight steps, while direct lane selection keeps processing behavior steady across a batch.

high-throughput document parsing
low-cost translation
subagent classification

How Borg uses it

Gemini 3.5 Flash-Lite is available as a subscription catalog lane in Borg. The catalog does not publish which Fusion profiles route to this model, so no routing role is claimed here. You can pick it directly by setting the OpenAI-compatible gateway model field to a listed lane id. Check the current catalog for availability before building a workflow around a lane.

model: "antigravity/gemini-3.5-flash-lite"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	1572 ms	4373 ms	33554
Tokens per second (end to end)	59.2 output tokens per second	278.5 output tokens per second	197556
Request success rate	100%	—	38840

Time to first token (gateway proxy)

Lower is fasterFleet median 3971.5 ms

Gemini 3.5 Flash-Lite1572 ms

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Gemini 3.5 Flash-Lite59.2 tokens/s

Time to first token (gateway proxy): time until the first streamed response event reaches the gateway; our closest available measure of time to first token
Tokens per second (end to end): tokens per second, end to end: provider-reported output tokens divided by the whole turn's elapsed time, including queueing and reasoning; not a streaming per-token rate

Share of requests Borg completed successfully, excluding requests the client cancelled.

Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.

Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 216821 requests. Minimum 100 samples per published request metric.

Benchmarks

Google-reported internal automated safety evaluations, relative to the comparator named below. These are changes in evaluation performance, not absolute capability scores or human red-team results. Google says updated evaluations are not directly comparable with results in earlier model cards. The vendor table reports percentage-point change: lower is better for safety and unjustified-refusal measures; higher is better for tone. Vendor evaluation details

Benchmark	Vendor-reported score	Source
Text-to-text safety vs Gemini 3.1 Flash-Lite	-8.14%	Vendor source
Multilingual safety vs Gemini 3.1 Flash-Lite	-0.92%	Vendor source
Tone vs Gemini 3.1 Flash-Lite	+3.04%	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $0.3 input / $2.5 output per 1M tokens. Vendor price source.

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite is listed in Borg's subscription catalog as antigravity/gemini-3.5-flash-lite. Gemini 3.5 Flash-Lite is the economical counterpart to 3.5 Flash, intended for quick, high-volume subagent tasks rather than lengthy deliberation.

Is Gemini 3.5 Flash-Lite in Borg?

Yes. Gemini 3.5 Flash-Lite is listed in Borg's subscription catalog under the lane antigravity/gemini-3.5-flash-lite. You can choose the lane directly, or explore the available Fusion profiles. Availability and model details can change; check the current catalog before deployment.

What context window does Gemini 3.5 Flash-Lite have?

The published context window is 1,048,576 tokens. Consult the cited sources for details and current limits. Vendor source

Is Gemini 3.5 Flash-Lite good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include high-throughput document parsing, low-cost translation, subagent classification. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Gemini 3.5 Flash-Lite on Borg?