Skip to content

Commit 446dcb8

Browse files
author
Jill Grant
authored
Merge pull request #277204 from aahill/cmk-update
Cmk update
2 parents d810c3c + 06e65d9 commit 446dcb8

File tree

2 files changed

+13
-3
lines changed

2 files changed

+13
-3
lines changed

articles/ai-services/openai/faq.yml

Lines changed: 6 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -248,6 +248,10 @@ sections:
248248
Can I bring my own data store to use with Assistants?
249249
answer: |
250250
No. Currently Assistants supports only local files uploaded to the Assistants-managed storage. You cannot use your private storage account with Assistants.
251+
- question: |
252+
Does Assistants support customer-managed key encryption (CMK)?
253+
answer: |
254+
Today we support CMK for Threads and Files in Assistants. See the [What's new page](./whats-new.md#customer-managed-key-cmk-support-for-assistants) for available regions for this feature.
251255
- question: |
252256
Is my data used by Microsoft for training models?
253257
answer: |
@@ -259,9 +263,8 @@ sections:
259263
- question: |
260264
How am I charged for Assistants?
261265
answer: |
262-
Currently, when you use Assistants API, you're billed for the following:
263-
- Inference cost (input and output) of the base model you're using for each Assistant (for example gpt-4-0125). If you've created multiple Assistants, you will be charged for the base model attached to each Assistant.
264-
- If you've enabled the Code Interpreter tool. For example if your assistant calls Code Interpreter simultaneously in two different threads, this would create two Code Interpreter sessions, each of which would be charged. Each session is active by default for one hour, which means that you would only pay this fee once if your user keeps giving instructions to Code Interpreter in the same thread for up to one hour.
266+
* Inference cost (input and output) of the base model you're using for each Assistant (for example gpt-4-0125). If you've created multiple Assistants, you will be charged for the base model attached to each Assistant.
267+
* If you've enabled the Code Interpreter tool. For example if your assistant calls Code Interpreter simultaneously in two different threads, this would create two Code Interpreter sessions, each of which would be charged. Each session is active by default for one hour, which means that you would only pay this fee once if your user keeps giving instructions to Code Interpreter in the same thread for up to one hour.
265268
266269
For more information, see the [pricing page](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/).
267270
- question: |

articles/ai-services/openai/whats-new.md

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -18,6 +18,13 @@ recommendations: false
1818

1919
This article provides a summary of the latest releases and major documentation updates for Azure OpenAI.
2020

21+
## June 2024
22+
23+
### Customer-managed key (CMK) support for Assistants
24+
25+
Threads and Files in Assistants now supports CMK in the following region:
26+
* West US 3
27+
2128
## May 2024
2229

2330
### GPT-4o provisioned deployments

0 commit comments

Comments
 (0)