Anthropic Launches Advisor Tool Cutting AI Agent Costs by 85%

Anthropic just dropped a tool that could reshape how developers budget for AI agents. The advisor tool, announced April 9, lets cheaper Claude models tap into Opus-level intelligence only when needed -- cutting costs by up to 85% while maintaining competitive performance.

The mechanic is straightforward: Sonnet or Haiku runs your agent end-to-end, handling tool calls and iterations. When it hits a wall, it escalates to Opus for guidance. Opus never touches tools or user output directly -- it just advises and hands control back.

Anthropic's benchmarks tell an interesting story. Sonnet with an Opus advisor scored 2.7 percentage points higher on SWE-bench Multilingual than Sonnet alone, while actually costing 11.9% less per task. That's better performance for less money -- not a tradeoff most developers expect.

Haiku users see even more dramatic shifts. On BrowseComp, Haiku with Opus advisor hit 41.2% -- more than double its solo score of 19.7%. Yes, it still trails Sonnet's standalone performance by 29%, but here's the kicker: it costs 85% less per task. For high-volume operations where you're burning through thousands of agent calls daily, that math gets very attractive very fast.

The timing isn't accidental. Anthropic shipped Sonnet 4.6 in mid-February, which already matched Opus-level performance in many tasks. OpenAI countered with GPT-5.4 in early March, unifying their Codex and GPT lines with million-token context. The AI agent space is getting crowded, and cost efficiency is becoming the battleground.

The advisor tool flips the typical orchestration pattern. Instead of a big model delegating to smaller workers, a cheap model drives everything and only escalates when stuck. No decomposition logic, no worker pools -- just a single API call with built-in handoffs.

Developers add one tool declaration to their Messages API request. The type routes context to Opus automatically when the executor model decides it needs help. A parameter caps advisor calls per request, and tokens bill at each model's respective rate.

Since Opus typically generates just 400-700 tokens of guidance per consultation while the executor handles full output at lower rates, overall spend stays well below running Opus end-to-end.

The tool slots alongside existing capabilities -- web search, code execution, whatever you're already using. No architectural overhaul required.

For teams already running Claude agents at scale, this is a straightforward optimization. For those evaluating Anthropic against OpenAI's expanding lineup, it's another variable in the cost-performance equation that's worth modeling before committing infrastructure.