Sonnet
Published Updated
What is Sonnet?
The balanced middle tier of the Claude model family. It is widely considered the sweet spot for agentic coding and general enterprise workloads.
Sonnet provides an optimal balance between high-end reasoning and execution speed. In the context of AI-assisted development, Sonnet (currently Claude Sonnet 5) is the de facto engine for most autonomous coding agents, offering near-Opus level coding capabilities at significantly lower latency and cost.
How it relates to Orbit
Orbit’s Model Tiers can route a tier to Sonnet, a common choice for Medium and High prompts. See Complexity Tiers & Routing for details.
When you would use it
You default to Sonnet for almost all software engineering and agent orchestration tasks, as it provides the best combination of reliability, code generation skill, and speed.
Common operations
- Powering autonomous coding agents in IDEs like Cline and Windsurf.
- Executing multi-step tool-calling workflows reliably.