Google · in Borg

Gemini 2.5 Pro

Gemini 2.5 Pro is the largest reasoning-oriented member of Google's 2.5 generation, aimed at problems where Flash and Flash-Lite may sacrifice depth for speed or price.

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

1,048,576 tokensContext window

—Median time to first token (gateway proxy)

95.3Output tokens per second (whole turn)

$1.25 / $10Vendor 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	2025-03-25 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
Knowledge cutoff	2025-01 Vendor source
Borg lane ids	`antigravity/gemini-2.5-pro`, `google/gemini-2.5-pro`, `google/gemini-2.5-pro-preview`
Versions in Borg	Gemini 2.5 Pro · Gemini 3.1 Pro
Median tokens per second (end to end) on Borg	95.3 output tokens per second

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

What Gemini 2.5 Pro is good for

Gemini 2.5 Pro is the largest reasoning-oriented member of Google's 2.5 generation, aimed at problems where Flash and Flash-Lite may sacrifice depth for speed or price. It reads lengthy codebases, documents, audio and video through a large shared context and produces text answers, plans or code. Adaptive thinking suits hard math, STEM and multi-stage software tasks; for short classification jobs, a Flash sibling is the more economical fit. Google prices longer prompts above its lower token band, so API cost depends on request size. Borg includes Pro within the subscription; Borg Fusion can route demanding work to it, or you can pick its lane directly when you prefer deliberate analysis over a lower-latency response.

long-repository code analysis
multi-step STEM reasoning
cross-document synthesis

How Borg uses it

Gemini 2.5 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-2.5-pro"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	—	—	59
Tokens per second (end to end)	95.3 output tokens per second	118.1 output tokens per second	315

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Gemini 2.5 Pro95.3 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; 400 requests. Minimum 100 samples per published request metric.

Pricing

Included in Borg subscription. Vendor API list price: $1.25 input / $10 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 2.5 Pro?

Gemini 2.5 Pro is listed in Borg's subscription catalog as antigravity/gemini-2.5-pro. Gemini 2.5 Pro is the largest reasoning-oriented member of Google's 2.5 generation, aimed at problems where Flash and Flash-Lite may sacrifice depth for speed or price.

Is Gemini 2.5 Pro in Borg?

Yes. Gemini 2.5 Pro is listed in Borg's subscription catalog under the lane antigravity/gemini-2.5-pro. 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 2.5 Pro have?

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

Is Gemini 2.5 Pro good for coding?

No vendor-published coding evaluation is listed here. Its listed uses include long-repository code analysis, multi-step STEM reasoning, cross-document synthesis. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Gemini 2.5 Pro on Borg?