Gemini 3.5 Flash-Lite is now available in ThinkReview

Gemini 3.5 Flash-Lite is now available in ThinkReview

We're excited to announce that Gemini 3.5 Flash-Lite is now available in ThinkReview. Google introduced it alongside Gemini 3.6 Flash and 3.5 Flash Cyber as the fastest, most cost-effective model in the 3.5 series — built for low latency and high-throughput agentic workloads. You can use it today for AI-powered code reviews on GitHub, GitLab, Azure DevOps, and Bitbucket.

What is Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite is Google's speed-and-efficiency option in the 3.5 Flash family. According to Google's announcement, it is designed for both low-latency tasks and high-volume workflows like agentic search and document processing — the same profile that fits frequent, affordable PR reviews.

Highlights from Google's launch:

• Fastest 3.5-class model — About 350 output tokens per second on the Artificial Analysis Index, with significantly better quality than prior Flash-Lite generations on agentic workflows.
• Strong price-to-performance — Priced at $0.30/1M input and $2.50/1M output tokens, built for high-throughput production traffic.
• Big step up over 3.1 Flash-Lite — Stronger coding and agentic results, including Terminal-Bench 2.1 (54% vs 31%), long context on GDM-MRCR v2 (72.2% vs 60.1%), and real-world task scores on GDPval-AA v2 (1140 vs 642).
• Outperforms Gemini 3 Flash on key evals — Including SWE-Bench Pro (54.2% vs 49.6%) and OSWorld-Verified (74.0% vs 65.1%), making it a faster, more capable option for many workloads that previously sat on older Flash models.
• Configurable thinking levels — Dial latency and cost down for high-volume tasks, or raise thinking for multi-step subagent-style work.
• Computer use built in — Available as a client-side tool via the Gemini API, supporting more reliable agentic execution across surfaces.

3.5 Flash-Lite is available via the Gemini API, Google AI Studio, Android Studio, Gemini Enterprise, and the Gemini app — and now inside ThinkReview for everyday pull request review.

Why use Gemini 3.5 Flash-Lite in ThinkReview

Code review at team scale needs models that stay sharp without blowing the latency or token budget. Flash-Lite is built for that trade-off.

• High-volume PR throughput — Faster output and lower cost help when you're reviewing many changes a day across repos and platforms.
• Better coding quality than prior Lite models — Stronger agentic and SWE-bench results mean sharper feedback on bugs, regressions, and implementation detail — not just cheaper tokens.
• Responsive on large diffs — Low latency keeps reviews feeling snappy even when the change set is wide.
• Flexible depth — Use lighter thinking for routine PRs; dial up when a multi-file or multi-step review needs more reasoning.
• Pairs with the rest of the Gemini catalog — Keep Gemini 3.5 Flash for deeper agentic work, and use 3.5 Flash-Lite when speed and cost matter most.

Whether you're on high-traffic teams or cost-sensitive workflows, Gemini 3.5 Flash-Lite is a strong default for fast, affordable reviews in ThinkReview.

How to use it in ThinkReview

1. Open ThinkReview settings — Click the extension icon and go to Settings or Model selection.
2. Choose Gemini 3.5 Flash-Lite — Select it from the model dropdown for your reviews.
3. Run a review — Open any pull request or merge request and start ThinkReview with your chosen model.

You can switch between models at any time. Use 3.5 Flash-Lite for high-volume or cost-sensitive reviews; switch to 3.5 Flash, Pro, or other models when you need a different depth/speed trade-off.

Manage models in Model Selection on the ThinkReview portal.

Where it works

Same as always: GitHub, GitLab, Azure DevOps, and Bitbucket Cloud. One extension, one workflow — now with Google's fastest 3.5-class Flash model for efficient AI reviews.

If you try Gemini 3.5 Flash-Lite on real PRs and have feedback, we'd love to hear it — open an issue on GitHub or reach out via thinkreview.dev.

Ready for faster, more cost-efficient AI code reviews? Install ThinkReview or manage your models in the portal.

Model details reference Google's Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber announcement.