Anthropic Advisor Strategy: Optimize Your Costs and Performance with Claude

The rapid evolution of LLMs presents a dilemma: should you prioritize the power of a model like Claude Opus, or the speed and cost-efficiency of a lighter model like Haiku? Anthropic is changing the game with the Advisor strategy.

This approach pairs Opus's intelligence with the efficiency of Sonnet or Haiku: a low-cost "executor" model handles routine tasks and only calls on the "advisor" (Opus) for complex reasoning.

The Concept and Cost Structure ▶ 0:00

The strategy is based on a simple observation: most tasks performed by an AI agent don't require maximum power at every step. If only one step out of three requires high-level reasoning, using Opus everywhere wastes resources.

On the pricing side ▶ 1:35: Opus costs $5/M input tokens and $25 output, Sonnet $3 / $15, and Haiku $1 / $5. With the Advisor strategy, the bulk of text generation is shifted to Haiku or Sonnet, reserving Opus's expensive tokens for critical decision-making. The strategy is available through the Messages API ▶ 2:16, with the max_uses parameter to limit Advisor interventions.

Demo: Performance Comparison ▶ 4:12

A customer support dashboard was tested with different configurations. For simple questions like "What are your business hours?", Haiku handles it efficiently on its own. Using Opus for the same question costs 21 times more for a nearly identical result.

Screenshot of a code editor displaying a markdown file with knowledge base information

For complex queries involving conditional product returns, the dynamic shifts. A notable finding: Sonnet, used as the executor, chose to call on the Opus Advisor where Haiku thought it could handle things on its own. The Sonnet + Opus result was significantly more nuanced, proving that the intermediate model has a better "awareness" of its own limitations.

Optimizing Claude Code with "Opus Plan" ▶ 10:31

In Claude Code, the /model opus plan command uses Opus for planning (problem understanding, architecture) and switches to Sonnet for code execution, which is faster and more cost-effective.

Slide with a cost calculator showing a chart comparing monthly costs across different modes

The financial impact is massive ▶ 13:59. Over 10,000 monthly requests (70% easy, 20% medium, 10% hard): up to 85% savings compared to Opus Solo, and about 23% compared to Sonnet Solo, all while benefiting from Opus's intelligence on complex tasks.

Conclusion

The Advisor strategy marks a major milestone: it shifts from a "brute force" approach to intelligent resource orchestration. Near-Opus performance at Haiku prices, control via max_uses, and opus plan mode in Claude Code to maximize your sessions. Still in beta, this feature represents the future of AI assistance: distributed intelligence where every cent spent delivers real value.