Anthropic 为降低成本将 Claude Fable 5 变为管理者，委派任务给 Sonnet 5

Anthropic's fix for Fable 5's high cost is turning it into a manager that delegates to Sonnet 5

AI 导读

鉴于 Claude Fable 5 成本高昂，Anthropic 建议将其主要用作规划器，执行交由较小模型。在“Advisor”模式下，Sonnet 5 作为执行者，仅在需要指导时调用 Fable 5；SWE-bench Pro 上性能达 Fable 5 独自的 92%，成本降至 63%，每次任务约调用一次 Fable 5。在“Planner”模式下，Fable 5 规划并委派任务给 Sonnet 5 智能体；BrowseComp 上性能达 96%，成本仅 46%。两种模式均通过 Claude Managed Agents 运行。此举正值价格压力加剧——中国开源模型已压低西方定价，新 GPT‑5.6 Sol 每 token 成本更低且 token 效率更高。

正文 · 原文

Claude Fable 5 is expensive. Anthropic now recommends using it mainly as a planner, handing execution off to smaller models. The Claude developer team outlines two strategies. In the "Advisor" pattern, Sonnet 5 runs as the executor and only calls Fable 5 when it needs guidance. On SWE-bench Pro, this combo reaches about 92 percent of Fable 5's solo performance at 63 percent of the cost, according to Anthropic. Fable 5 gets called roughly once per task.

Advisor pattern: Sonnet 5 does the work and only consults Fable 5 when needed. | Image: Anthropic

In the second pattern, Fable 5 acts as a planner that delegates tasks to Sonnet 5 worker agents. On BrowseComp, this delivers 96 percent of Fable 5's performance at 46 percent of the cost. Both patterns run through Claude Managed Agents, with each sub-agent using its own cache to avoid duplicate context costs. The official documentation has more details.

Orchestrator pattern: Fable 5 plans and distributes tasks to multiple Sonnet 5 workers. | Image: Anthropic

Anthropic is likely sharing these tips because of growing price pressure. Chinese open-source models are already undercutting Western pricing, and the new GPT-5.6 Sol is much cheaper per token and reportedly more token-efficient too.