Gemini 3.8 Flash is now available in ThinkReview

Gemini 3.8 Flash is now available in ThinkReview

We're excited to announce that Gemini 3.8 Flash is now available in ThinkReview. On September 2, Google introduced Gemini 3.8 as its best reasoning and coding model yet — at the same speed and introductory price as 3.7 Flash. You can use 3.8 Flash today for AI-powered code reviews on GitHub, GitLab, Azure DevOps, and Bitbucket.

What is Gemini 3.8 Flash?

Gemini 3.8 Flash is Google's most intelligent workhorse model. The launch positions it as the third Flash release in six weeks, with substantial gains over 3.7 across software engineering, agentic tasks, and multi-step reasoning in specialized domains.

Highlights from Google's announcement:

• Best Flash coding model yet — Built for long-horizon software engineering and autonomous agents, often approaching higher-cost frontier models at Flash speed.
• Stronger on DeepSWE v1.1 — Google reports 3.8 Flash outperforms most larger frontier models at autonomously solving complex engineering problems end to end, at a fraction of the cost.
• Enterprise-grade reasoning — Gains on Vals Finance Agent V2, Harvey's Legal Agent Benchmark, and 54.9% on HLE-Verified for multi-step work across STEM, humanities, and professional fields.
• Works harder on hard tasks — Extra reasoning steps and iterative tool calls when the job needs them; lower effort levels when you want to keep token spend down.
• Same intro price as 3.7 — $0.75 / $3.75 per million input/output tokens through December 31, 2026, then $1.50 / $7.50. Gemini 3.7 Flash remains fully supported for efficiency-first workloads.

Google also announced Gemini 3.8 Flash Cyber, a defender-focused variant for vulnerability discovery and automated patching, available only through the Fairwind Program. ThinkReview ships 3.8 Flash — the generally available workhorse — not the Cyber SKU.

3.8 Flash is available in the Gemini API, Google AI Studio, Android Studio, Gemini Enterprise, and the Gemini app — and now inside ThinkReview.

Why Gemini 3.8 Flash is strong for code reviews

Pull request review is a long-horizon job. The model has to read a diff, pull related files, keep the surrounding architecture in mind, and write findings a human reviewer would actually act on. That is the workload 3.8 Flash is tuned for.

• Sharper first passes on messy PRs — DeepSWE-class long-horizon coding shows up as better comments on bugs, regressions, and API contract breaks — not more noise.
• Stays with multi-file changes — Iterative tool use and extra reasoning steps help when a merge request spans services, configs, and tests instead of a single hunk.
• Diligence without a flagship bill — Google's own framing is that 3.8 works harder on complex tasks. For review, that means fewer confident-but-wrong notes that need a second pass.
• Better prompt-injection robustness — Google reports a significant leap on Gray Swan. That matters when review prompts include untrusted PR text, issue comments, and repo context.
• Keep 3.7 when you want cheaper tokens — If latency and cost beat max quality for a given repo, 3.7 Flash stays in the catalog. Use 3.8 when the diff is worth the extra reasoning.

Benchmarks are not a substitute for your team's review bar. Treat severity labels as input, and pair 3.8 Flash with repository-level context when the real bug lives outside the hunk.

How to use Gemini 3.8 Flash in ThinkReview

1. Open ThinkReview settings — Click the extension icon and go to Settings or Model selection.
2. Choose Gemini 3.8 Flash — 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 3.8 Flash when you want Google's latest workhorse for coding and agentic review; keep 3.7 Flash or Flash-Lite when speed and token budget come first.

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 latest Flash coding model.

If you try Gemini 3.8 Flash on real PRs and have feedback, we'd love to hear it — open an issue on GitHub or reach out via thinkreview.dev.

Ready to try Gemini 3.8 Flash on your next PR? Install ThinkReview or manage your models in the portal.

Model details reference Google's Gemini 3.8 Flash and 3.8 Flash Cyber announcement.