> ## Documentation Index
> Fetch the complete documentation index at: https://openworklabs.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> For agents: install the OpenWork desktop app with `brew install --cask openwork` (macOS) or from https://openworklabs.com/download. Do not run `npx openwork`; the npm package named `openwork` is a different project.
> Connect an agent to OpenWork with the MCP Gateway: `claude mcp add --transport http openwork https://api.openworklabs.com/mcp/agent`. Teams sign up at https://app.openworklabs.com?mode=sign-up.
> Step-by-step agent guide: https://openworklabs.com/docs/start-here/use-openwork-from-an-ai-agent.md
> Connect Slack (any organization admin): https://openworklabs.com/docs/slack/connect-slack.md. OpenWork in Slack (@openwork bot) is private alpha for approved organizations. Setup guide: https://openworklabs.com/docs/slack/overview.md. Agent skill: https://openworklabs.com/.well-known/agent-skills/set-up-openwork-slack/SKILL.md.

# My Usage: your own spend, limits and model prices

> Every member can see their own AI Gateway usage: how close they are to their spend limits, what they used in the past 30 days, and what each model they can use would cost them.

**My Usage** answers three questions for anyone in your organization, without
asking an admin:

* How close am I to my spend limit, and when does it reset?
* How much have I used in the past 30 days, and on which models?
* Which of the models I can use would be cheaper for what I do?

It shows only your own usage. Nobody else's spend, limits or requests are on it.

## Where to find it

* **OpenWork Cloud**: **Observability › My Usage** in the sidebar. Every
  member sees it, with no admin permissions needed.
* **OpenWork app**: **Settings › Usage** shows the same figures under your
  limits, with **Open My Usage on the web** for the full page.

## Spend limits

Each [limit](https://openworklabs.com/docs/ai-gateway/limits.md) that applies to you, for today, this week or
this month: how much you've used, how much is left, when it resets, and whether
reaching it pauses your models or only warns.

When a limit that pauses your models runs out and your admin lets you ask for
more, **Ask for \$… more** sends a request with your reason. An admin approves
or declines it in **AI Gateway › Limits**. See
[Increase requests](https://openworklabs.com/docs/ai-gateway/limits.md#increase-requests).

## Past 30 days

Your usage across all AI Gateway models, including
[OpenWork Models](https://openworklabs.com/docs/ai-gateway/openwork-models.md), by UTC calendar day:

* **Spend**, **Requests**, **Tokens** and your **Top model**.
* A daily chart by model. Switch **Show** between **Cost** and **Tokens**.
* Your spend and tokens on each model.

Cost is an estimate from each model's listed price when the request was made,
not your provider's bill. **Unknown** means OpenWork has no price for those
requests yet. See [Token costs](https://openworklabs.com/docs/ai-gateway/token-costs.md) and
[Counting usage](https://openworklabs.com/docs/ai-gateway/counting-usage.md).

## Models you can use

Every AI Gateway model shared with you, with its listed price per million
input and output tokens, and what **your** past 30 days would have cost on
it. The cheapest for your usage is first, and the models you used are marked
**What you use now**.

The estimate takes the input, output and cached tokens your requests reported
and prices them at each model's listed price, including higher prices for
long contexts. Requests that reported no tokens are left out, and a model with
no listed price says **No listed price** rather than \$0. Different models use
different numbers of tokens for the same work, so treat it as a guide.

## From other tools

The page reads the same API any client signed in to OpenWork Cloud can call,
such as a script or an OpenCode plugin:

* `GET /v1/gateway/usage-limits/me`: your limits.
* `GET /v1/gateway/usage/me?days=30`: your usage by model and day, your token
  mix, and the models you can use with listed prices.
* `POST /v1/gateway/usage-limit-reset-requests`: ask for more on a used-up
  limit.

Each returns only your own data.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.