@@ -12,26 +12,28 @@ The default quota for models varies by model and region. Default quota limits ar
12
12
13
13
Quota for standard deployments is described in of terms of [ Tokens-Per-Minute (TPM)] ( ../../how-to/quota.md ) .
14
14
15
- | Region | GPT-4 | GPT-4-32K | GPT-4-Turbo | GPT-4-Turbo-V | GPT-35-Turbo | GPT-35-Turbo-Instruct | Text-Embedding-Ada-002 | text-embedding-3-small | text-embedding-3-large | Babbage-002 | Babbage-002 - finetune | Davinci-002 | Davinci-002 - finetune | GPT-35-Turbo - finetune | GPT-35-Turbo-1106 - finetune | GPT-35-Turbo-0125 - finetune |
16
- | :-----------------| :-------:| :-----------:| :-------------:| :---------------:| :--------------:| :-----------------------:| :------------------------:| :------------------------:| :------------------------:| :-------------:| :------------------------:| :-------------:| :------------------------:| :-------------------------:| :------------------------------:| :-------------------------------|
17
- | australiaeast | 40 K | 80 K | 80 K | 30 K | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
18
- | brazilsouth | - | - | - | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
19
- | canadaeast | 40 K | 80 K | 80 K | - | 300 K | - | 350 K | 350 K | 350 K | - | - | - | - | - | - | - |
20
- | eastus | - | - | 80 K | - | 240 K | 240 K | 240 K | 350 K | 350 K | - | - | - | - | - | - | - |
21
- | eastus2 | - | - | 80 K | - | 300 K | - | 350 K | 350 K | 350 K | - | - | - | - | 250 K | 250 K | 250 K |
22
- | francecentral | 20 K | 60 K | 80 K | - | 240 K | - | 240 K | - | 350 K | - | - | - | - | - | - | - |
23
- | japaneast | - | - | - | 30 K | 300 K | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
24
- | northcentralus | - | - | 80 K | - | 300 K | - | 350 K | - | - | 240 K | 250 K | 240 K | 250 K | 250 K | 250 K | 250 K |
25
- | norwayeast | - | - | 150 K | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
26
- | southafricanorth | - | - | - | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
27
- | southcentralus | - | - | 80 K | - | 240 K | - | 240 K | - | - | - | - | - | - | - | - | - |
28
- | southindia | - | - | 150 K | - | 300 K | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
29
- | swedencentral | 40 K | 80 K | 150 K | 30 K | 300 K | 240 K | 350 K | - | 350 K | 240 K | 250 K | 240 K | 250 K | 250 K | 250 K | 250 K |
30
- | switzerlandnorth | 40 K | 80 K | - | 30 K | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
31
- | switzerlandwest | - | - | - | - | - | - | - | - | - | - | 250 K | - | 250 K | 250 K | 250 K | 250 K |
32
- | uksouth | - | - | 80 K | - | 240 K | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
33
- | westeurope | - | - | - | - | 240 K | - | 240 K | - | - | - | - | - | - | - | - | - |
34
- | westus | - | - | 80 K | 30 K | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
35
- | westus3 | - | - | 80 K | - | - | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
15
+ | Region | GPT-4 | GPT-4-32K | GPT-4-Turbo | GPT-4-Turbo-V | gpt-4o | gpt-4o - GlobalStandard | GPT-35-Turbo | GPT-35-Turbo-Instruct | Text-Embedding-Ada-002 | text-embedding-3-small | text-embedding-3-large | Babbage-002 | Babbage-002 - finetune | Davinci-002 | Davinci-002 - finetune | GPT-35-Turbo - finetune | GPT-35-Turbo-1106 - finetune | GPT-35-Turbo-0125 - finetune |
16
+ | :-----------------| :-------:| :-----------:| :-------------:| :---------------:| :--------: | :-------------------------: | :-------- ------:| :-----------------------:| :------------------------:| :------------------------:| :------------------------:| :-------------:| :------------------------:| :-------------:| :------------------------:| :-------------------------:| :------------------------------:| :-------------------------------|
17
+ | australiaeast | 40 K | 80 K | 80 K | 30 K | - | - | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
18
+ | brazilsouth | - | - | - | - | - | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
19
+ | canadaeast | 40 K | 80 K | 80 K | - | - | - | 300 K | - | 350 K | 350 K | 350 K | - | - | - | - | - | - | - |
20
+ | eastus | - | - | 80 K | - | 150 K | 450 K | 240 K | 240 K | 240 K | 350 K | 350 K | - | - | - | - | - | - | - |
21
+ | eastus2 | - | - | 80 K | - | 150 K | 450 K | 300 K | - | 350 K | 350 K | 350 K | - | - | - | - | 250 K | 250 K | 250 K |
22
+ | francecentral | 20 K | 60 K | 80 K | - | - | - | 240 K | - | 240 K | - | 350 K | - | - | - | - | - | - | - |
23
+ | japaneast | - | - | - | 30 K | - | - | 300 K | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
24
+ | northcentralus | - | - | 80 K | - | 150 K | 450 K | 300 K | - | 350 K | - | - | 240 K | 250 K | 240 K | 250 K | 250 K | 250 K | 250 K |
25
+ | norwayeast | - | - | 150 K | - | - | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
26
+ | southafricanorth | - | - | - | - | - | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
27
+ | southcentralus | - | - | 80 K | - | 150 K | 450 K | 240 K | - | 240 K | - | - | - | - | - | - | - | - | - |
28
+ | southindia | - | - | 150 K | - | - | - | 300 K | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
29
+ | swedencentral | 40 K | 80 K | 150 K | 30 K | - | - | 300 K | 240 K | 350 K | - | 350 K | 240 K | 250 K | 240 K | 250 K | 250 K | 250 K | 250 K |
30
+ | switzerlandnorth | 40 K | 80 K | - | 30 K | - | - | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
31
+ | switzerlandwest | - | - | - | - | - | - | - | - | - | - | - | - | 250 K | - | 250 K | 250 K | 250 K | 250 K |
32
+ | uksouth | - | - | 80 K | - | - | - | 240 K | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
33
+ | westeurope | - | - | - | - | - | - | 240 K | - | 240 K | - | - | - | - | - | - | - | - | - |
34
+ | westus | - | - | 80 K | 30 K | 150 K | 450 K | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
35
+ | westus3 | - | - | 80 K | - | 150 K | 450 K | - | - | 350 K | - | 350 K | - | - | - | - | - | - | - |
36
36
37
- 1 K = 1000 Tokens-Per-Minute (TPM). The relationship between TPM and Requests Per Minute (RPM) is [ currently defined as 6 RPM per 1000 TPM] ( ../../how-to/quota.md#understanding-rate-limits ) .
37
+ 1 K = 1000 Tokens-Per-Minute (TPM). The relationship between TPM and Requests Per Minute (RPM) is [ currently defined as 6 RPM per 1000 TPM] ( ../../how-to/quota.md#understanding-rate-limits ) .
38
+
39
+ The values for GPT-4o in the table above represent default quota values that are available to all customers. Enterprise customers have much larger [ quota allocations] ( ../../quotas-limits.md#gpt-4o-rate-limits ) .
0 commit comments