MAI-Thinking-1

Reasoning playground

Run long-context reasoning prompts against Microsoft's MAI-Thinking-1 preview model.

Calls the Foundry resource route /mai/v1/chat/completions. The deployment name is sent as model.

Connection

Foundry base endpoint: https://resource.services.ai.azure.com or https://resource.openai.azure.com

Model controls

Encrypted reasoning is returned on the final stream event or non-streaming response, kept only in memory, and passed back unchanged on later turns. It is redacted from payload previews, cURL, logs, auto-save, and exported sessions.

Start a MAI-Thinking-1 conversation

Provide a reasoning task, configure your Foundry deployment, and generate an answer.

An unhandled error has occurred. Reload 🗙