June 2, 2026 · Anthropic

Advisor tool adds max_tokens; refused requests with no output no longer billed

The advisor tool now supports a max_tokens parameter to cap the advisor model’s output for each call, reducing latency and output token cost for workloads that don’t need full-length advisor responses. Set tools[].max_tokens on the advisor tool definition; see Capping advisor output.
On the Claude API, you are no longer billed for a request when it returns stop_reason: "refusal" without Claude having generated any output. See Streaming refusals for detecting and handling refusals.