Google · in Borg

Gemini 3.6 Flash

Gemini 3.6 Flash is Google's later third-generation workhorse following 3.5 Flash.

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

1,048,576 tokensContext window

5009 msMedian time to first token (gateway proxy)

56.8Output tokens per second (whole turn)

$0.75 / $3.75Vendor 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-3.6-flash-high`, `antigravity/gemini-3.6-flash-low`, `antigravity/gemini-3.6-flash-medium`, `antigravity/gemini-3.6-flash-tiered`, `google/gemini-3.6-flash`
Versions in Borg	Gemini 2.5 Flash · Gemini 3 Flash · Gemini 3.5 Flash · Gemini 3.6 Flash · Gemini 3.7 Flash · Gemini 3.8 Flash
Median time to first token (gateway proxy) on Borg	5009 ms
Median tokens per second (end to end) on Borg	56.8 output tokens per second

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

What Gemini 3.6 Flash is good for

Gemini 3.6 Flash is Google's later third-generation workhorse following 3.5 Flash. Its published positioning emphasizes more efficient tokens and better coding, agentic planning and spatial understanding, while keeping Flash's speed-oriented place below the Pro tier. It reads audio, pictures, video, PDFs and text in a large window and returns text, making it suitable for repository edits, multimodal reasoning and repeated tool calls. The official API price has an introductory period, so external per-token cost is not a timeless property of this release. It is distinct from the smaller 3.5 Flash-Lite, which favors simpler high-volume extraction. Borg includes 3.6 Flash in the subscription; Fusion can route suitable work to it, or you can select one of its effort-specific lanes directly.

rapid agentic coding loops
spatial reasoning from visual inputs
multistep tool execution

How Borg uses it

Gemini 3.6 Flash 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-3.6-flash-high"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	5009 ms	18828 ms	5875
Tokens per second (end to end)	56.8 output tokens per second	375.9 output tokens per second	33413

Time to first token (gateway proxy)

Lower is fasterFleet median 3971.5 ms

Gemini 3.6 Flash5009 ms

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Gemini 3.6 Flash56.8 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

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; 33654 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 3.5 Flash	-1.35%	Vendor source
Multilingual safety vs Gemini 3.5 Flash	-5.45%	Vendor source
Unjustified refusals vs Gemini 3.5 Flash	+0.25%	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $0.75 input / $3.75 output per 1M tokens. Vendor price source.

Introductory rates through December 31, 2026. From January 1, 2027: $1.50 input / $7.50 output / $0.15 cached input per 1M tokens. Vendor pricing terms

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Gemini 3.6 Flash?

Gemini 3.6 Flash is listed in Borg's subscription catalog as antigravity/gemini-3.6-flash-high. Gemini 3.6 Flash is Google's later third-generation workhorse following 3.5 Flash.

Is Gemini 3.6 Flash in Borg?

Yes. Gemini 3.6 Flash is listed in Borg's subscription catalog under the lane antigravity/gemini-3.6-flash-high. 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 3.6 Flash have?

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

Is Gemini 3.6 Flash good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include rapid agentic coding loops, spatial reasoning from visual inputs, multistep tool execution. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Gemini 3.6 Flash on Borg?