Claude Sonnet 5 is now available in ThinkReview

July 10, 2026
Thinkode AI
3 min read
ClaudeClaude Sonnet 5AnthropicAI Code ReviewPull RequestsModel SelectionThinkReviewCode Quality

Claude Sonnet 5 is now available in ThinkReview

We're excited to announce that Claude Sonnet 5 is now available in ThinkReview. Anthropic released Claude Sonnet 5 as the most agentic Sonnet yet — built to plan, use tools, and follow through on multi-step work at a level that recently required larger, more expensive models. You can use it today for AI-powered code reviews on GitHub, GitLab, Azure DevOps, and Bitbucket.

What is Claude Sonnet 5?

Sonnet 5 is Anthropic's next-generation mid-tier model: a substantial upgrade over Sonnet 4.6 on reasoning, tool use, coding, and knowledge work, with performance that narrows the gap to Opus 4.8 at lower cost.

Highlights from Anthropic's launch:

  • Most agentic Sonnet yet — Plans, drives browsers and terminals, and sustains autonomous work instead of stalling mid-task.
  • Near-Opus on the work that matters — Stronger coding and tool-use scores than Sonnet 4.6, with high-effort settings that can match Opus 4.8 on some agentic tasks.
  • Effort control — Tune depth vs. cost so a one-line fix doesn't burn the same budget as a cross-service refactor.
  • 1M-token context — Large enough for big diffs and related project context when ThinkReview integrations can fetch it.
  • Introductory API pricing — $2 / $10 per million input/output tokens through August 31, 2026, then standard Sonnet pricing.

Developers call it via the API as claude-sonnet-5. In ThinkReview, you'll find it in Model selection on the Professional tier.

Why Sonnet 5 is a strong fit for code review

Pull request review is exactly the workload Sonnet 5 targets: sustained coding analysis, tool-aware follow-through, and technical grounding across messy brownfield changes.

  • Root-cause reviews — Early testers highlight strength on race conditions, hidden tests, and failures that need tracing past the first symptom.
  • Multi-file follow-through — Better at finishing complex explorations instead of stopping halfway through a large MR.
  • Actionable, code-centric feedback — Concrete findings you can accept, dismiss, or send to Cursor, Claude Code, or GitHub Copilot via implement-from-review deeplinks.
  • Better cost/performance than Opus for daily volume — Use Opus when you need maximum depth; use Sonnet 5 when you want near-flagship agentic quality across more PRs.

How to use Claude Sonnet 5 in ThinkReview

  1. Open ThinkReview settings — Click the extension icon and go to Settings or Model selection.
  2. Choose Claude Sonnet 5 — 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.

Claude Sonnet 5 is available on Professional (and plans that include Professional models). Manage your catalog in Model Selection on the ThinkReview portal.

For the deepest reviews, connect a platform integration so the model can use repository-level context during analysis.

Where it works

Same as always: GitHub, GitLab, Azure DevOps, and Bitbucket Cloud. One extension, one workflow — now with Anthropic's latest Sonnet-class agentic model.

If you try Claude Sonnet 5 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 near-Opus reviews at Sonnet efficiency? Install ThinkReview or manage your models in the portal.

Model details reference Anthropic's Claude Sonnet 5 announcement.