Google · in Borg

Gemini 3.1 Pro

Gemini 3.1 Pro is the heavier reasoning tier of Google's Gemini 3 lineup, refining the earlier 3 Pro for better thinking, token efficiency and reliable multi-step tool use.

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

1,048,576 tokensContext window

—Median time to first token (gateway proxy)

—Output tokens per second (whole turn)

$2 / $12Vendor API price in / out · per 1M

Included in Borg

Download Borg Borg for Business

At a glance

Preview API model: gemini-3.1-pro-preview. Availability and limits may change. Vendor availability source

Specification	Value
Provider	Google
Family	Gemini
Release date	2026-02-19 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-3.1-pro-high`, `antigravity/gemini-3.1-pro-low`, `google/gemini-3.1-pro-preview`
Versions in Borg	Gemini 2.5 Pro · Gemini 3.1 Pro

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

What Gemini 3.1 Pro is good for

Gemini 3.1 Pro is the heavier reasoning tier of Google's Gemini 3 lineup, refining the earlier 3 Pro for better thinking, token efficiency and reliable multi-step tool use. Unlike Flash-Lite's throughput focus, this preview targets complex software engineering, long-context analysis and tasks that require careful planning across mixed text, image, video, audio and PDF inputs. It returns text rather than generated images, and Google's pricing has a higher band for prompts beyond the shorter-input threshold. A separate custom-tools endpoint exists, but it should not be confused with the ordinary preview lane here. Borg includes 3.1 Pro in the subscription; Borg Fusion can route difficult tasks to it, or you can choose its lane directly when you want a consistent Pro-level response.

complex software engineering
multi-step tool-driven agents
long-context multimodal research

How Borg uses it

Gemini 3.1 Pro 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-3.1-pro-high"

Measured on Borg

Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 278 requests. Minimum 100 samples per published request metric.

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

Borg served 278 requests for this model in the last 30 days; not enough timed samples to publish a speed figure yet.

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 +0.10% text-to-text and +0.11% multilingual results are explicitly qualified as non-egregious. Vendor evaluation details

Benchmark	Vendor-reported score	Source
Text-to-text safety vs Gemini 3 Pro	+0.10%	Vendor source
Multilingual safety vs Gemini 3 Pro	+0.11%	Vendor source
Image-to-text safety vs Gemini 3 Pro	-0.33%	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $2 input / $12 output per 1M tokens. Vendor price source.

Rates for prompts of at most 200,000 tokens; longer prompts cost more. Vendor pricing terms

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Gemini 3.1 Pro?

Gemini 3.1 Pro is listed in Borg's subscription catalog as antigravity/gemini-3.1-pro-high. Gemini 3.1 Pro is the heavier reasoning tier of Google's Gemini 3 lineup, refining the earlier 3 Pro for better thinking, token efficiency and reliable multi-step tool use.

Is Gemini 3.1 Pro in Borg?

Yes. Gemini 3.1 Pro is listed in Borg's subscription catalog under the lane antigravity/gemini-3.1-pro-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 3.1 Pro have?

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

Is Gemini 3.1 Pro good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include complex software engineering, multi-step tool-driven agents, long-context multimodal research. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Gemini 3.1 Pro on Borg?