Oossa

Anthropic adds server tool flags to its API models

Anthropic now reports which models can use web search and code execution tools via new capabilities.server_tools fields.

NoteBy Published by Oossa: 1 min read

Event date:

Anthropic updated its API on October 6, 2026. The Models API now includes a capabilities.server_tools section. It shows whether each model supports web search and code execution tools. Developers can read capabilities.server_tools.code_execution to see if a model accepts code execution, and capabilities.code_execution to know if code can call other tools.

Why it matters

Developers can programmatically verify a model’s tool support, avoiding runtime errors when using search or code execution features.

Was this article useful?
Share

Read next

Oossa · Newsletter

The week in AI, explained

Every Monday: the stories worth knowing, in plain language. Free, no spam.