Claude Sonnet 4.6 is Here
Anthropic's most capable Sonnet yet — approaching Opus-level intelligence at Sonnet pricing. Try it free in Code Reviewer and Kilo Cloud to celebrate the launch.
Why Sonnet 4.6
Opus-level intelligence at a fraction of the cost
Opus-Level Intelligence
Users preferred Sonnet 4.6 over Opus 4.5 59% of the time. Get frontier-class performance without the frontier price tag.
79.6% SWE-bench Verified
Near the top of the field for agentic coding, rivaling models costing significantly more.
1M Token Context
Reason effectively across entire codebases, contracts, and research papers with a 1 million token context window.
Less Lazy, More Reliable
Significantly less prone to overengineering and laziness. Better instruction following, fewer hallucinations, fewer false claims of success.
Agentic Powerhouse
59.1% on Terminal-Bench 2.0, 72.5% on OSWorld for computer use, 91.7% on τ-bench Retail for tool use.
Beautiful Frontend Code
Notably more polished visual outputs with better layouts, animations, and design sensibility. Fewer rounds of iteration needed.
Free to Try — Celebrate the Launch
Experience Sonnet 4.6 at no cost in Code Reviewer and Kilo Cloud
Free in Code Reviewer
Get AI-powered code reviews using Sonnet 4.6 — completely free during the launch celebration. Review your PRs with Opus-level intelligence.
Start Reviewing →Free in Kilo Cloud
Run Sonnet 4.6 agents in the cloud with zero cost during launch week. Build, debug, and ship code with the most capable Sonnet ever.
Open Kilo Cloud →Sonnet 4.6 Benchmark Performance
Approaching Opus-level scores at Sonnet pricing
Read the full announcement →| Benchmark | Sonnet 4.6 | Opus 4.6 | Sonnet 4.5 |
|---|---|---|---|
| SWE-bench Verified | 79.6% | 80.8% | 77.2% |
| Terminal-Bench 2.0 | 59.1% | 65.4% | 51.0% |
| OSWorld-Verified | 72.5% | 72.7% | 61.4% |
| τ-bench Retail | 91.7% | 91.9% | 86.2% |
| BrowseComp | 74.7% | 84.0% | 43.9% |
| ARC-AGI-2 | 58.3% | 68.8% | 13.6% |
| GPQA Diamond | 89.9% | 91.3% | 83.4% |
| Finance Agent v1.1 | 63.3% | 60.1% | 54.5% |
How to use Claude Sonnet 4.6
Get started in minutes
Install Kilo Code
Install the Kilo Code extension in VS Code, JetBrains, or use the CLI.
Select Claude Sonnet 4.6
Choose claude-sonnet-4-6 from the model picker in any mode.
Or Try Code Reviewer
Visit kilo.ai/code-reviewer and get free Sonnet 4.6 code reviews on your PRs.
Or Try Kilo Cloud
Visit kilo.ai/cloud and run Sonnet 4.6 agents in the cloud for free during launch.
Start Building
Use Code, Architect, Debug, or Orchestrator mode with Opus-level intelligence.
Trusted by developers at the world's most innovative companies
Other affordable and free models available in Kilo Code
Not just Sonnet 4.6 — explore 500+ models including free options and budget-friendly high-performers
Free Models for Everyday Coding
Start building without spending a cent
Nemotron 3 Super
NVIDIA's 120B-parameter open hybrid MoE model — only 12B active per token. Ranks in Kilo's top coding models this week, and it's free.
Ling-2.6-flash
inclusionAI's instant instruct model, 104B total / 7.4B active parameters. Fast, capable, and a regular fixture in the daily leaderboard's free tier.
MiniMax M2.5
SOTA large language model built for real-world productivity. The free variant gives you MiniMax M2.5 performance at zero cost.
Affordable High-Performers
Frontier-level quality at a fraction of the cost
Grok Code Fast 1
The model that powered the free frontier era. Kilo Coders have been using over 700B tokens per month. Now at a remarkably low price point.
MiniMax M2.1
Competitive performance on practical coding benchmarks. Reliable for production use cases at a fraction of frontier model costs.
GLM 4-7
Open-weight model with strong agentic coding capabilities. Handles multi-phase implementation tasks with excellent context understanding.
Gemini 3 Flash Preview
Outperforms Gemini 3 Pro on many benchmarks at 1/4 the cost. Excellent for high-volume coding tasks.
Agentic Engineering
Glide through your workflow with a mode for every step
Ask mode
A knowledgeable technical assistant focused on answering questions without changing your codebase
Use Kilo Everywhere
Kilo works where you work. Build alone or with your team.
Frequently Asked Questions
Compare Kilo Code with Other Tools
See how Kilo Code stacks up against other AI coding assistants
Kilo Code vs Cursor
The open-source agentic platform inside your existing IDE vs the standalone AI-first code editor. 500+ models, zero markup, no editor switch required.
Kilo Code vs GitHub Copilot
Multi-model, multi-mode agentic coding vs a single-vendor autocomplete from GitHub.
Kilo Code vs Windsurf
500+ models at exact provider rates. No credit system. Full BYOK on all plans. Open source.
Kilo Code vs Claude Code
Open-source, multi-model CLI + IDE agent with inline autocomplete vs Anthropic's Claude-only terminal-first coding agent.
Kilo Code vs Roo Code
Roo Code archives May 15, 2026 — compare it with Kilo Code and migrate in minutes.
Kilo Code vs Cline
Kilo Code bundles Cline-style autonomy plus Orchestrator, Architect, Debug, and Code modes.
Kilo Code vs Tabnine
Full agentic coding across 500+ models vs Tabnine's enterprise-only autocomplete.
Kilo Code vs Augment Code
Open-source, BYOK-everywhere agent platform vs Augment Code's closed proprietary stack.
Kilo Code vs Lovable
Kilo Code plugs into your real IDE and codebase — Lovable is a hosted AI app builder optimized for greenfield prototyping.
Kilo Code vs Replit
Use Kilo inside your existing editor and infrastructure vs Replit's hosted browser IDE.
Kilo Code vs Amp Code
Amp Code is shutting down its VS Code extension — compare it with Kilo Code
Kilo Code for JetBrains IDEs
AI coding assistant for IntelliJ, PhpStorm, WebStorm, and Rider
Start Using Claude Sonnet 4.6 Today
Opus-level intelligence. Sonnet pricing. Free in Code Reviewer and Kilo Cloud.