Google · in Borg

Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite is the smallest, fastest and lowest-cost option in the 2.5 lineup, below Flash and substantially lighter than Pro.

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

1,048,576 tokensContext window

776 msMedian time to first token (gateway proxy)

62.2Output tokens per second (whole turn)

100%Request success

$0.1 / $0.4Vendor 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	2025-06-17 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-flash-lite`, `google/gemini-2.5-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	776 ms
Median tokens per second (end to end) on Borg	62.2 output tokens per second

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

What Gemini 2.5 Flash-Lite is good for

Gemini 2.5 Flash-Lite is the smallest, fastest and lowest-cost option in the 2.5 lineup, below Flash and substantially lighter than Pro. It accepts audio, video, images and PDFs as well as text but returns text, making it useful for routing messages, labeling content and extracting fields from many short or long records. Thinking is supported, although paying for extended reasoning can defeat the point of choosing this lightweight model. Its large input window helps with bulk document handling while its inexpensive token rate favors repetitive requests. Google currently restricts new API access to the older 2.5 generation. Borg includes Flash-Lite in the subscription; Borg Fusion can choose it for economical routine work, or you can select its lane explicitly for predictable throughput.

cheap high-volume classification
structured extraction from PDFs
low-latency message triage

How Borg uses it

Gemini 2.5 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-2.5-flash-lite"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	776 ms	3049 ms	1830274
Tokens per second (end to end)	62.2 output tokens per second	324.2 output tokens per second	13383618
Request success rate	100%	—	2593761

Time to first token (gateway proxy)

Lower is fasterFleet median 3971.5 ms

Gemini 2.5 Flash-Lite776 ms

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Gemini 2.5 Flash-Lite62.2 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; 18326188 requests. Minimum 100 samples per published request metric.

Pricing

Included in Borg subscription. Vendor API list price: $0.1 input / $0.4 output per 1M tokens. Vendor price source.

Input and cache rates shown are for text/image/video, not audio. Vendor pricing terms

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite is listed in Borg's subscription catalog as antigravity/gemini-2.5-flash-lite. Gemini 2.5 Flash-Lite is the smallest, fastest and lowest-cost option in the 2.5 lineup, below Flash and substantially lighter than Pro.

Is Gemini 2.5 Flash-Lite in Borg?

Yes. Gemini 2.5 Flash-Lite is listed in Borg's subscription catalog under the lane antigravity/gemini-2.5-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 2.5 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 2.5 Flash-Lite good for coding?

No vendor-published coding evaluation is listed here. Its listed uses include cheap high-volume classification, structured extraction from PDFs, low-latency message triage. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Gemini 2.5 Flash-Lite on Borg?