Anthropic added max_tokens for the advisor tool to cap advisor model output per call.

This matters when advisor responses do not need full length, cutting latency and output token cost.

Set tools[].max_tokens on the advisor tool definition when workloads need capped advisor output.

• Jun 11, 2026OpenAI modelcard diff shows the API docs navigation content removed.
• Jun 11, 2026OpenAI pricing page removed visible API pricing content for GPT-5.5, GPT-5.4, and realtime.
• Jun 11, 2026Anthropic launched Claude Fable 5 and Claude Mythos 5 with 1M context and 128k max output.

This is the world we build in. It moves this fast. We move with it.