M365 Copilot Console

Sign in to chat and manage your API access.

Powered by Microsoft 365 Copilot · OpenAI-compatible
M365 Copilot Console

Start a conversation

Default model is gpt-5.6-think-deeper. Attach text files or images (receipts, screenshots) — images are sent to Copilot's vision.

Usage statistics — all sessions, web + API combined

Current chat session

Send a message to start collecting stats for this chat.

Requests, tokens & cost over time

successful requests failed requests est. tokens

By model

By account

By source

Sessions (click a row for full context)

Token counts are estimates (~chars/4) — M365 Copilot does not expose exact token usage. Cost is what those tokens would have cost at standard pay-per-token list prices (M365 itself is flat-rate), so it is an estimate built on an estimate.

Audit & access — who signed in, when, from where, how

Clients (distinct source · IP · client)

Recent sign-in events

"From where" is the client IP (via X-Forwarded-For); geolocation isn't resolved (offline). "How" is derived from the User-Agent.

M365 accounts

Each account is one set of M365 credentials with its own login, its own Copilot Studio agent and its own rate-limit budget. Pick one per chat, or pin an API token to it.

API tokens

One token per client. Bind a token to an account and that client can only ever spend those credentials; leave it on Any and the client picks per request (X-M365-Account header or an account/model model id).

Base URL

Point any OpenAI-compatible client here:

Usage examples

Default model: gpt-5.6-think-deeper. All models from the selector work here.