End‑user plans & quotas

When you sell an app with AI features, your customers are on your plans: free, pro, team. Worksi can enforce those plans on every model call. Tell the gateway who the end user is and which of your plans they are on, and an end_user_quota policy decides how much they may use.

1. Send the end user and their plan#

Add two headers to each gateway call:

import osfrom openai import OpenAI client = OpenAI(    base_url="https://gateway.worksi.ai/v1",    api_key=os.environ["AIW_API_KEY"],) def answer(    user_id_hash: str,    user_plan: str,    messages: list[dict],) -> str | None:    headers = {        # a pseudonymous id, not an email        "X-AIW-End-User": user_id_hash,        # your own plan name, e.g. "free"        "X-AIW-End-User-Plan": user_plan,    }    res = client.chat.completions.create(        model="gpt-5-mini",        messages=messages,        extra_headers=headers,    )    return res.choices[0].message.content

import OpenAI from "openai" const client = new OpenAI({  baseURL: "https://gateway.worksi.ai/v1",  apiKey: process.env.AIW_API_KEY,}) export async function answer(  userIdHash,  userPlan,  messages,) {  const headers = {    // a pseudonymous id, not an email    "X-AIW-End-User": userIdHash,    // your own plan name, e.g. "free"    "X-AIW-End-User-Plan": userPlan,  }  const res = await client.chat    .completions.create(      { model: "gpt-5-mini", messages },      { headers },    )  return res.choices[0]?.message.content}

With the Python SDK, set them once on the run and every call inside it carries them:

with aiw.run("customer-chat", end_user=user_id_hash, end_user_plan="free"):    ...

2. Create an end‑user quota policy#

Create an end‑user quota policy in Governance → Policies, or post it to /api/v1/policies. Every limit is per end user and each one is optional.

{  "name": "Plan limits for app users",  "type": "end_user_quota",  "scope_type": "org",  "enforcement": "enforce",  "rules": {    "plans": {      "free": {        "requests_per_day": 50,        "tokens_per_day": 50000,        "models": ["gpt-5-mini"]      },      "pro": {        "requests_per_day": 2000,        "cost_usd_per_month": 20      }    },    "default_plan": "free"  }}

Plan names use lowercase letters, digits, - and _. Like every policy, the quota can be scoped to the whole organization, a workspace, an environment, an agent, a workflow or a team, and it can start in monitor mode, which records what would have been limited without blocking anyone.

3. Handle the limits in your app#

Blocked calls never reach your provider, so they cost nothing, and they don’t count toward your Worksi plan’s monthly requests.

4. See usage per end user#

Performance → End users lists your end users with requests, tokens, cost, errors, plan and last activity. Filter by plan or search for a user, and open one to see their usage over time and their recent traces. Every span also carries the plan as aiw.end_user_plan.

Good practice#

• Hash user ids with a secret salt before sending them. The end‑user id is stored as it is and is not redacted.
• Keep plan names in step with your billing system, so every user gets the limits they pay for.
• Start in monitor mode for a few days, compare what would have been limited with what you expect, then enforce.
• End‑user plans and quotas are included in every Worksi plan.