GPT-5.6 Luna is now available in ThinkReview
GPT-5.6 Luna is now available in ThinkReview
We're excited to announce that GPT-5.6 Luna is now available in ThinkReview. OpenAI's GPT-5.6 family — Luna, Terra, and Sol — brings frontier-generation intelligence across three sizes. Luna is the fast, affordable tier: strong capability at the lowest cost in the 5.6 lineup. You can use it today for AI-powered code reviews on GitHub, GitLab, Azure DevOps, and Bitbucket.
What is GPT-5.6 Luna?
Luna is the efficiency-focused member of GPT-5.6. Where Sol is the flagship and Terra the balanced mid tier, Luna is built for speed and volume without leaving the 5.6 generation behind.
What stands out for reviewers:
- Frontier-family model at Lite cost — Part of the same GPT-5.6 release as Sol and Terra, tuned for cheaper, faster workloads.
- Strong everyday coding intelligence — Useful for extraction-style checks, clear bug findings, and high-volume PR coverage.
- Large context window — GPT-5.6 models ship with a million-token context class and high max output — helpful when diffs and related files grow.
- Reasoning effort you can scale — Pair Luna with higher effort when a PR needs more depth, or keep it light for routine changes.
- API pricing aimed at abundance — Roughly $1 / $6 per million input/output tokens on OpenAI's published Luna rates — built for teams that review often.
In ThinkReview, GPT-5.6 Luna is on the Lite tier — a practical upgrade path when Free-tier models aren't enough but you don't need Professional every time.
Why use GPT-5.6 Luna in ThinkReview
Code review is a high-frequency workload. Luna fits the PRs you run all day: feature branches, dependency bumps, UI tweaks, and mid-size refactors that still deserve a real model.
- Better default for Lite users — Modern GPT-5.6 quality without jumping straight to Professional frontier models.
- Faster feedback loops — Lower latency helps reviews feel interactive on the PR page.
- Sensible credit use — Keep flagship models for risky changes; let Luna cover the rest of the queue.
- Same ThinkReview workflow — Select GPT-5.6 Luna once; use it across GitHub, GitLab, Azure DevOps, and Bitbucket.
If you need deeper analysis on the same family, see our companion post on GPT-5.6 Luna Pro for the higher-effort Professional option.
How to use it in ThinkReview
- Open ThinkReview settings — Click the extension icon and go to Settings or Model selection.
- Choose GPT-5.6 Luna — 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.
GPT-5.6 Luna is available on Lite (and plans that include Lite models). Manage your catalog in Model Selection.
Where it works
Same as always: GitHub, GitLab, Azure DevOps, and Bitbucket Cloud. One extension, one workflow — now with OpenAI's GPT-5.6 Luna for everyday AI reviews.
If you try GPT-5.6 Luna 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 frontier-family reviews at Lite speed? Install ThinkReview or manage your models in the portal.
Model details reference OpenAI's GPT-5.6 announcement and related GPT-5.6 family coverage.