The advisor tool now supports max_tokens to cap advisor output per call.

Builders can limit advisor responses when workloads do not need full-length output, reducing latency and output token cost.

Set tools[].max_tokens on the advisor definition for workloads that need capped advisor output.

• Aug 25, 2026OpenAI models page removed visible model selection documentation text.
• Aug 25, 2026Anthropic model card removed Claude Fable 5 and Claude Mythos 5 selection guidance
• Aug 25, 2026OpenAI removed business pricing copy listing GPT-5.6 and GPT-Image-2 rates.

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