Merge pull request #265132 from kbrowne8/kbrowne8-patch-3

prmerger-automator[bot] · web-flow · commit b82ca667a30a · 2024-02-07T23:00:23.000Z
Update gpt-with-vision.md
diff --git a/articles/ai-services/openai/concepts/gpt-with-vision.md b/articles/ai-services/openai/concepts/gpt-with-vision.md
@@ -62,13 +62,33 @@ Base Pricing for GPT-4 Turbo with Vision is:
 
 See the [Tokens section of the overview](/azure/ai-services/openai/overview#tokens) for information on how text and images translate to tokens.
 
-Additionally, if you use video prompt integration with the Video Retrieval add-on, it accrues other costs:
-- Ingestion: $0.05 per minute of video
-- Transactions: $0.25 per 1000 queries of the Video Retrieval index
+If you turn on Enhancements, additional usage applies for using GPT-4 Turbo with Vision with Azure AI Vision functionality.
 
-Processing videos involves the use of extra tokens to identify key frames for analysis. The number of these additional tokens will be roughly equivalent to the sum of the tokens in the text input, plus 700 tokens.
+| Model        | Price        |
+|-----------------|-----------------|
+| + Enhanced add-on features for OCR | $1.5 per 1000 transactions |
+| + Enhanced add-on features for Object Detection | $1.5 per 1000 transactions |
+| + Enhanced add-on feature for “Add your Image” Image Embeddings | $1.5 per 1000 transactions |
+| + Enhanced add-on feature for “Video Retrieval” integration **<sup>1</sup>** | Ingestion: $0.05 per minute of video <br>Transactions: $0.25 per 1000 queries of the Video Retrieval index |
 
-### Example price calculation
+**<sup>1</sup>** Processing videos involves the use of extra tokens to identify key frames for analysis. The number of these additional tokens will be roughly equivalent to the sum of the tokens in the text input, plus 700 tokens.
+
+### Example image price calculation
+> [!IMPORTANT]
+> The following content is an example only, and prices are subject to change in the future.
+
+For a typical use case, take an image with both visible objects and text and a 100-token prompt input. When the service processes the prompt, it generates 100 tokens of output. In the image, both text and objects can be detected. The price of this transaction would be:
+
+| Item        | Detail        | Total Cost   |
+|-----------------|-----------------|--------------|
+| GPT-4 Turbo with Vision input tokens | 100 text tokens | $0.001 |
+| Enhanced add-on features for OCR | $1.50 / 1000 transactions | $0.0015 |
+| Enhanced add-on features for Object Grounding | $1.50 / 1000 transactions | $0.0015 | 
+| Output Tokens      | 100 tokens (assumed)    | $0.003       |
+| **Total Cost** |  | $0.007 |
+
+
+### Example video price calculation
 
 > [!IMPORTANT]
 > The following content is an example only, and prices are subject to change in the future.
diff --git a/articles/ai-services/openai/includes/gpt-v-python.md b/articles/ai-services/openai/includes/gpt-v-python.md
@@ -22,7 +22,7 @@ Use this article to get started using the Azure OpenAI Python SDK to deploy and
     Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form at https://aka.ms/oai/access. Open an issue on this repo to contact us if you have an issue. 
 - <a href="https://www.python.org/" target="_blank">Python 3.7.1 or later version</a>.
 - The following Python libraries: `os`
-- An Azure OpenAI Service resource with a GPT-4 Turbo with Vision model deployed. The resource must be in the `SwitzerlandNorth`, `SwedenCentral`, `WestUS`, or `AustraliaEast` Azure region. For more information about model deployment, see [the resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
+- An Azure OpenAI Service resource with a GPT-4 Turbo with Vision model deployed. See [GPT-4 and GPT-4 Turbo Preview model availability](../concepts/models.md#gpt-4-and-gpt-4-turbo-preview-model-availability) for available regions. For more information about resource creation, see the [resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
 - For Vision enhancement (optional): An Azure Computer Vision resource in the same region as your Azure OpenAI resource, in the paid (S0) tier.
 
 ## Set up 
diff --git a/articles/ai-services/openai/includes/gpt-v-rest.md b/articles/ai-services/openai/includes/gpt-v-rest.md
@@ -18,7 +18,7 @@ Use this article to get started using the Azure OpenAI REST APIs to deploy and u
 - Access granted to Azure OpenAI in the desired Azure subscription. Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form at https://aka.ms/oai/access. Open an issue on this repo to contact us if you have an issue. 
 - <a href="https://www.python.org/" target="_blank">Python 3.7.1 or later version</a>.
 - The following Python libraries: `requests`, `json`.
-- An Azure OpenAI Service resource with a GPT-4 Turbo with Vision model deployed. The resource must be in the `SwitzerlandNorth`, `SwedenCentral`, `WestUS`, or `AustraliaEast` Azure region. For more information about model deployment, see [the resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
+- An Azure OpenAI Service resource with a GPT-4 Turbo with Vision model deployed. See [GPT-4 and GPT-4 Turbo Preview model availability](../concepts/models.md#gpt-4-and-gpt-4-turbo-preview-model-availability) for available regions. For more information about resource creation, see the [resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
 - For Vision enhancement (optional): An Azure Computer Vision resource in the same region as your Azure OpenAI resource, in the paid (S0) tier.
 
 > [!NOTE]
diff --git a/articles/ai-services/openai/includes/gpt-v-studio.md b/articles/ai-services/openai/includes/gpt-v-studio.md
@@ -16,7 +16,7 @@ Start exploring GPT-4 Turbo with Vision capabilities with a no-code approach thr
 
 - An Azure subscription. <a href="https://azure.microsoft.com/free/ai-services" target="_blank">Create one for free</a>.
 - Access granted to Azure OpenAI in the desired Azure subscription. Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form at https://aka.ms/oai/access. Open an issue on this repo to contact us if you have an issue. 
-- An Azure OpenAI Service resource. The resource must be in the `SwitzerlandNorth`, `SwedenCentral`, `WestUS`, or `AustraliaEast` Azure region. For more information about resource creation, see the [resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
+- An Azure OpenAI Service resource with a GPT-4 Turbo with Vision model deployed. See [GPT-4 and GPT-4 Turbo Preview model availability](../concepts/models.md#gpt-4-and-gpt-4-turbo-preview-model-availability) for available regions. For more information about resource creation, see the [resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
 - For Vision enhancement (optional): An Azure Computer Vision resource in the same region as your Azure OpenAI resource, in the paid (S0) tier.
 
 > [!NOTE]
