You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/openai/quotas-limits.md
+20-11Lines changed: 20 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ ms.custom:
9
9
- ignite-2023
10
10
- references_regions
11
11
ms.topic: conceptual
12
-
ms.date: 4/08/2025
12
+
ms.date: 4/09/2025
13
13
ms.author: mbullwin
14
14
---
15
15
@@ -86,7 +86,7 @@ The following sections provide you with a quick guide to the default quotas and
86
86
>
87
87
> This is particularly important for programmatic model deployment as this change in RPM/TPM ratio can result in accidental under allocation of quota if one is still assuming the 1:1000 ratio followed by older chat completion models.
88
88
>
89
-
> There is a known issue with the [quota/usages API](/rest/api/aiservices/accountmanagement/usages/list?view=rest-aiservices-accountmanagement-2024-06-01-preview&tabs=HTTP&preserve-view=true) where it assumes the old ratio applies to the new o1-series models. The API returns the correct base capacity number, but doesn't apply the correct ratio for the accurate calculation of TPM.
89
+
> There's a known issue with the [quota/usages API](/rest/api/aiservices/accountmanagement/usages/list?view=rest-aiservices-accountmanagement-2024-06-01-preview&tabs=HTTP&preserve-view=true) where it assumes the old ratio applies to the new o1-series models. The API returns the correct base capacity number, but doesn't apply the correct ratio for the accurate calculation of TPM.
90
90
91
91
### `o-series` global standard
92
92
@@ -199,14 +199,18 @@ If your Azure subscription is linked to certain [offer types](https://azure.micr
199
199
200
200
|Tier| Quota Limit in tokens per minute (TPM) |
201
201
|---|:---|
202
-
|Azure for Students, Free Trials | 1 K (all models) <br>Exception o-series & GPT 4.5 Preview: 0|
203
-
| MSDN | GPT 3.5 Turbo Series: 30 K <br> GPT-4 series: 8 K <br>computer-use-preview: 30 K <br> gpt-4o-realtime-preview: 1 K <br> o-series: 0 <br> GPT 4.5 Preview: 0 |
204
-
|Pay-as-you-go | GPT 3.5 Turbo Series: 30 K <br> GPT-4 series: 8 K <br>computer-use-preview: 30 K <br> o-series: 0 <br> GPT 4.5 Preview: 0 |
205
-
| CSP Dev Test<sup>*</sup> | All models: 0 |
202
+
|`Azure for Students`| 1 K (all models) <br>Exception o-series & GPT 4.5 Preview: 0|
203
+
|`MSDN`| GPT-4o-mini: 200 K <br> GPT 3.5 Turbo Series: 200 K <br> GPT-4 series: 50 K <br>computer-use-preview: 8 K <br> gpt-4o-realtime-preview: 1 K <br> o-series: 0 <br> GPT 4.5 Preview: 0 |
204
+
|`Pay-as-you-go`| GPT-4o-mini: 200 K <br> GPT 3.5 Turbo Series: 200 K <br> GPT-4 series: 50 K <br>computer-use-preview: 30 K <br> o-series: 0 <br> GPT 4.5 Preview: 0 |
205
+
|`Azure_MS-AZR-0111P` <br> `Azure_MS-AZR-0035P` <br> `Azure_MS-AZR-0025P` <br> `Azure_MS-AZR-0052P` <br>| GPT-4o-mini: 200 K <br> GPT 3.5 Turbo Series: 200 K <br> GPT-4 series: 50 K |
206
+
|`CSP Integration Sandbox` <sup>*</sup> | All models: 0 |
207
+
|`Lightweight trial`<br>`Free Trials`<br>`Azure Pass`| All models: 0 |
206
208
207
-
<sup>*</sup>This only applies to a small number of dev/test CSP subscriptions. Use the query below to determine what `quotaId` is associated with your subscription.
208
209
209
-
To determine the offer type that is associated with your subscription you can check your `quotaId`. If your `quotaId` is not listed in this table your subscription qualifies for default quota.
210
+
211
+
<sup>*</sup>This only applies to a small number of legacy CSP sandbox subscriptions. Use the query below to determine what `quotaId` is associated with your subscription.
212
+
213
+
To determine the offer type that is associated with your subscription you can check your `quotaId`. If your `quotaId` isn't listed in this table your subscription qualifies for default quota.
210
214
211
215
# [REST](#tab/REST)
212
216
@@ -247,14 +251,19 @@ az rest --method GET --uri "https://management.azure.com/subscriptions/{sub-id}?
247
251
}
248
252
```
249
253
250
-
| Quota allocation | Subscription quota ID |
254
+
| Quota allocation/Offer type| Subscription quota ID |
0 commit comments