← all entries
A-TIER technique

Claude advisor mode — Opus plans, Sonnet or Haiku executes for less

chase.h.ai · 2026-04-10T01:11:03.000Z · in AI Saves, Vol. 6
Open post ↗

100k ft — What is this?

Claude advisor mode — Opus plans, Sonnet or Haiku executes for less
techniqueA-tier

50k ft — Why care?

Anthropic's advisor strategy runs Sonnet or Haiku as the tool-calling executor with Opus as a no-tools advisor that plans and replans when the executor gets stuck. Cited result: Sonnet plus Opus advisor scored 74.8 vs 72.1 at far lower cost; available via API or /advisor in Claude Code.
LLMagents

10k ft — Key takeaways

• Escalate to the advisor only on blockers. • Keep the expensive model tool-free to cap its token cost. • Try /advisor in Claude Code before hand-rolling routing.

5k ft — Tools & techniques

Claude, Claude API, Claude Code AI agents, API integration, advisor strategy, planner-executor split

1k ft — Deep-dive / try it

Comment “agent” for my Claude code guides
Transcript excerpt
And the topic just released advisor mode, which gives us better performance with Sonnet and Hiku at a cheaper cost. So the way the advisor strategy works is we have an agent that is executing tasks. It's either going to be Sonnet or Hiku and it has Opus, the more powerful model as the advisor. Opus comes with the plan. This is like having Opus plan mode and having Sonnet actually generate the code. The difference is, this is a little more sophisticated than that, because if the agent say Sonnet or Hiku starts working on Opus's plan, but it runs into a problem, well, it's going to go back to Opus and say, hey, here's the issue. What should we do? Opus then gives it a new updated plan for it to execute on. Now Opus also has full context of what's happening, but Opus doesn't make any tool calls, which is why we're able to keep the costs low even when we bring it in to advise. And because that advice is so much better than what Sonnet or Hiku normally generate, we're able to get better performance like you see on this graph at a cheaper cost. So here Sonnet with Opus advisor scored 74.8 versus 72.1 and it was at 96 cents versus $8.9. This held up across multiple benchmarks and you can use it both as an API or using slash advisor inside of Cloud Code.

Appears in

More from @chase.h.ai

Collection: AI Saves, Vol. 6