# Anthropic adds 'thinking disabled' flag to API model listings

> Anthropic’s API now shows whether a model has thinking turned off via a new capabilities flag.

Oossa · 2026-10-06 · https://oossa.com/en/anthropic-adds-thinking-disabled-flag-to-api-model-listings

Event date: 2026-10-05

Anthropic updated its API on October 5, 2026. The Models API now includes a new field called capabilities.thinking.types.disabled. When you call GET /v1/models or GET /v1/models/{model_id}, the response tells you if a model has thinking turned off (type: "disabled"). This lets developers see at a glance which models can use the thinking feature.

## The facts

- Added capabilities.thinking.types.disabled to the Models API on 2026-10-05
- GET /v1/models and GET /v1/models/{model_id} now report thinking status

## Why it matters

Developers can now programmatically avoid models that have thinking disabled, preventing unexpected behavior in applications.

## Sources & references

1. [docs.anthropic.com: October 5, 2026](https://docs.anthropic.com/en/release-notes/api#october-5-2026) – Anthropic API, 2026-10-05

Last updated: 2026-10-06