Merge pull request #252955 from gojira/keijik/turbo-instruct-0926

Add Turbo Instruct model

Author: prmerger-automator[bot]

articles/ai-services/openai/concepts/models.md

@@ -38,14 +38,15 @@ The `gpt-4` model supports 8192 max input tokens and the `gpt-4-32k` model suppo
 
 ## GPT-3.5
 
-GPT-3.5 models can understand and generate natural language or code. The most capable and cost effective model in the GPT-3.5 family is GPT-3.5 Turbo, which has been optimized for chat and works well for traditional completions tasks as well.  We recommend using GPT-3.5 Turbo over [legacy GPT-3.5 and GPT-3 models](./legacy-models.md).
+GPT-3.5 models can understand and generate natural language or code. The most capable and cost effective model in the GPT-3.5 family is GPT-3.5 Turbo, which has been optimized for chat and works well for traditional completions tasks as well. GPT-3.5 Turbo is available for use with the Chat Completions API. GPT-3.5 Turbo Instruct has similar capabilities to `text-davinci-003` using the Completions API instead of the Chat Completions API.  We recommend using GPT-3.5 Turbo and GPT-3.5 Turbo Instruct over [legacy GPT-3.5 and GPT-3 models](./legacy-models.md).
 
 - `gpt-35-turbo`
 - `gpt-35-turbo-16k`
+- `gpt-35-turbo-instruct`
 
-The `gpt-35-turbo` model supports 4096 max input tokens and the `gpt-35-turbo-16k` model supports up to 16,384 tokens.
+The `gpt-35-turbo` model supports 4096 max input tokens and the `gpt-35-turbo-16k` model supports up to 16,384 tokens.  `gpt-35-turbo-instruct` supports 4097 max input tokens.
 
-Like GPT-4, use the Chat Completions API to use GPT-3.5 Turbo. To learn more about how to interact with GPT-3.5 Turbo and the Chat Completions API check out our [in-depth how-to](../how-to/chatgpt.md).
+To learn more about how to interact with GPT-3.5 Turbo and the Chat Completions API check out our [in-depth how-to](../how-to/chatgpt.md).
 
 ## Embeddings models
 
@@ -97,6 +98,7 @@ GPT-3.5 Turbo is used with the Chat Completion API. GPT-3.5 Turbo (0301) can als
 | `gpt-35-turbo`<sup>1</sup> (0301) | East US, France Central, South Central US, UK South, West Europe | N/A | 4,096 | Sep 2021 |
 | `gpt-35-turbo` (0613) | Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South | N/A | 4,096 | Sep 2021 |
 | `gpt-35-turbo-16k` (0613) | Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South | N/A | 16,384 | Sep 2021 |
+| `gpt-35-turbo-instruct` (0914) | East US, Sweden Central | N/A | 4,097 | Sep 2021 |
 
 <sup>1</sup> Version `0301` of gpt-35-turbo will be retired no earlier than July 5, 2024.  See [model updates](#model-updates) for model upgrade behavior.
 

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

@@ -16,6 +16,10 @@ keywords:
 
 ## September 2023
 
+### GPT-3.5 Turbo Instruct
+
+Azure OpenAI Service now supports the GPT-3.5 Turbo Instruct model. This model has performance comparable to `text-davinci-003` and is available to use with the Completions API. Check the [models page](concepts/models.md), for the latest information on model availability in each region.
+
 ### Whisper public preview
 
 Azure OpenAI Service now supports speech to text APIs powered by OpenAI's Whisper model. Get AI-generated text based on the speech audio you provide. To learn more, check out the [quickstart](./whisper-quickstart.md).