GPT-5.4 mini is now available in ThinkReview
GPT-5.4 mini is now available in ThinkReview
We're excited to announce that GPT-5.4 mini is now available in ThinkReview — including on the Free plan. OpenAI introduced GPT-5.4 mini as one of its most capable small models yet: fast, efficient, and tuned for coding and high-volume workloads. You can use it today for AI-powered code reviews on GitHub, GitLab, Azure DevOps, and Bitbucket.
What is GPT-5.4 mini?
GPT-5.4 mini brings much of the strength of the larger GPT-5.4 line into a smaller, lower-latency package. OpenAI positions it for coding assistants, subagents, tool use, and workloads where response time shapes the experience.
Highlights from OpenAI's launch:
- Most capable small model class — Approaches full GPT-5.4 performance on coding and computer-use evals while staying fast.
- More than 2× faster than GPT-5 mini — Better turnaround when you're reviewing many PRs or iterating on feedback.
- Built for coding workflows — Strong on targeted edits, navigation, front-end generation, and debugging loops.
- Large context for a mini — 400k context window in the API, with support for tools and multimodal inputs.
- Cost-efficient — Priced for high-volume use ($0.75 / $4.50 per million input/output tokens on the OpenAI API).
In ThinkReview, GPT-5.4 mini is listed under the Free tier with a large max patch size — a strong default when you want responsive reviews without burning Professional credits.
Why use GPT-5.4 mini in ThinkReview
Not every PR needs a flagship model. Many changes need a sharp, fast pass: style and correctness checks, obvious bugs, and clear suggestions you can act on immediately.
- High-throughput reviews — Ideal when your team ships many small-to-medium PRs and latency matters.
- Strong free-tier option — Get modern OpenAI coding intelligence without upgrading just to try the model.
- Good first pass before deeper models — Run mini for routine changes; switch to Sonnet, Luna Pro, or Opus when the risk is higher.
- Same workflow everywhere — Pick GPT-5.4 mini once and use it across all supported platforms.
How to use it in ThinkReview
- Open ThinkReview settings — Click the extension icon and go to Settings or Model selection.
- Choose GPT-5.4 mini — Select it from the model dropdown for your reviews.
- Run a review — Open any pull request or merge request and start ThinkReview with your chosen model.
Manage models in Model Selection on the ThinkReview portal. You can switch between models at any time.
Where it works
Same as always: GitHub, GitLab, Azure DevOps, and Bitbucket Cloud. One extension, one workflow — now with OpenAI's fast GPT-5.4 mini for everyday review volume.
If you try GPT-5.4 mini 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 fast AI code reviews? Install ThinkReview or manage your models in the portal.
Model details reference OpenAI's GPT-5.4 mini and nano announcement.