MAI-Code-1.1-Flash

Coding playground

Hydrating page from local storage...

Generate, refactor, and debug code with Microsoft's text-and-image coding model. Attach source files or screenshots, then inspect the proposed changes before using them.

Tools

Web grounding source

None Web Search WebIQ

Both use WebIQ credentials. Choose WebIQ for more verticals.

Additional tools

X MCP

Read-only access to X through MCP.

Connection

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

MAI-Code-1.1-Flash calls the Foundry resource route /mai/v1/chat/completions. The deployment name is sent as model.

API

Foundry Resource Endpoint

Deployment Name

Authentication Mode

API Key

Stream

Advanced

Model controls

Max Completion Tokens

Use Reasoning Use Reasoning: Off

Reasoning Effort

Encrypted reasoning continuity Encrypted reasoning: Off

Encrypted reasoning continuity is documented for MAI-Thinking Chat Completions. This control stays Off and unavailable for MAI-Code and MAI Responses.

The catalog lists a 256,000-token context window and at most 64,000 completion tokens. Input, reasoning, and output share the available context. Generated code is not executed automatically.

Template

System Prompt

Start a MAI-Code-1.1-Flash conversation

Choose a coding example, attach source files or a screenshot when needed, and configure your Foundry deployment.