Anthropic Unveils Claude Advisor Strategy Pairing Opus With Sonnet to Cut AI Costs
Generative AI applications often face a trade-off between model capability and inference costs. The high-end Claude Opus is suited to complex judgments, but using it throughout a task is more expensive. Anthropic’s new “Advisor strategy” assigns tasks to Sonnet or Haiku and consults Opus only for critical decisions, concentrating advanced reasoning resources where they are needed.
On April 9, 2026, Anthropic launched the advisor tool in beta on the Claude Platform. Developers can configure Opus 4.6 to guide Sonnet 4.6 within a single Messages API request. Company tests showed a 2.7-percentage-point improvement on SWE-bench Multilingual and an 11.9% reduction in the cost of each agent task, or roughly 12%.
All Coverage
1 original reportsThe Backstory
The history behind this eventAnthropic Launches Claude Sonnet 5 With Near-Opus Performance and 60% Lower API Pricing
Anthropic’s Claude Sonnet series is designed to balance speed, cost and reasoning capabilities for software development, AI agents and enterprise knowledge work. Sonnet 5 brings performance across several areas closer to the flagship Claude Opus 4.8, allowing developers to deploy long-running workflows and computer-use tasks without paying top-tier model rates. That improves the cost-effectiveness of enterprise generative AI adoption.
Anthropic launched Claude Sonnet 5 on June 30, 2026, with support for a 1 million-token context window and output of up to 128,000 tokens. Through August 31, promotional API pricing is $2 per million input tokens and $10 per million output tokens, 60% below Opus 4.8’s respective rates of $5 and $25. Prices will rise to $3 and $15 on September 1.
Subscribe to Mark Radar Weekly
Every Friday, the week's strongest signals in your inbox. Unsubscribe anytime.
If you search news on Google, you can set Mark Radar as a preferred source—our coverage will show up more often in your results. Set as preferred source on Google →