https://docs.ai.gwdg.de/en/categories/sla/index.htmlHugoenhttps://docs.ai.gwdg.de/en/user/basics/request/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/user/basics/request/index.htmlHow a request is checked Every request passes three gates before it reaches a model: the API key it was made with, the user account that key belongs to, and the organisation that account belongs to. Each gate holds its own set of limits, split into the two kinds above: a request rate, counted in requests, and a budget, counted in euros. The request is measured against every limit that is set at that level, and it is rejected the moment any one of them is out of allowance, without the later gates being consulted. Only when all three gates pass does the request reach a model, and its cost is then written back to the budgets of all three levels at once.https://docs.ai.gwdg.de/en/technical/saia-platform/limits_budget/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/technical/saia-platform/limits_budget/index.htmlFrom a contract to a budget An organisation’s budgets come from what it has bought: Step Calculation Example Annual budget by contract 72,000 € Monthly budget annual ÷ 12 6,000 € Daily budget monthly ÷ 15 400 € The daily figure is divided by 15, not 30, and that is deliberate. At ÷ 30 you could never use more than an even day’s share, and a deadline or a teaching week would hit the wall. Dividing by 15 gives roughly twice the even daily rate as burst allowance: heavy days are possible, and sustaining that pace all month is not.https://docs.ai.gwdg.de/en/technical/saia-platform/limits_rate/index.htmlMon, 01 Jan 0001 00:00:00 +0000https://docs.ai.gwdg.de/en/technical/saia-platform/limits_rate/index.htmlHow did we calculate rate and budget limits for each organization? Two separate questions, with different answers. An organisation’s limits are derived from its contract, so that what it bought and what it may spend per day agree. The unit that connects euros to requests A budget is measured in euros and a rate limit in requests, so translating one into the other needs a conversion factor. Derived from real usage statistics at GWDG: An average request consist of roughly 10,000 tokens, which at around 1 € per million tokens comes to about 0.01 € per request.