Skip to content

Commit 3ada203

Browse files
committed
models for realtime
1 parent 3049188 commit 3ada203

File tree

1 file changed

+15
-15
lines changed

1 file changed

+15
-15
lines changed

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

Lines changed: 15 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -96,7 +96,7 @@ Once access has been granted, you will need to create a deployment for the model
9696

9797
| Model ID | Description | Context Window | Max Output Tokens | Training Data (up to) |
9898
| --- | :--- |:--- |:---|:---: |
99-
| `computer-use-preview` (2025-03-11) | Specialized model for use with the [Responses API](../how-to/responses.md) computer use tool <br> <br>-Tools <br>-Streaming<br>-Text(input/output)<br>- Image(input) | 8,192 | 1,024 | Oct 2023 |
99+
| `computer-use-preview` (2025-03-11) | Specialized model for use with the [Responses API](../how-to/responses.md) computer use tool <br> <br>-Tools <br>-Streaming<br>-Text(input/output)<br>- Image(input) | 8,192 | 1,024 | October 2023 |
100100

101101

102102
## GPT-4.5 Preview
@@ -111,7 +111,7 @@ Once access has been granted, you will need to create a deployment for the model
111111

112112
| Model ID | Description | Context Window | Max Output Tokens | Training Data (up to) |
113113
| --- | :--- |:--- |:---|:---: |
114-
| `gpt-4.5-preview` (2025-02-27) <br> **GPT-4.5 Preview** | [GPT 4.1](#gpt-41-series) is the recommended replacement for this model. Excels at diverse text and image tasks. <br>- Structured outputs <br>- Prompt caching <br>- Tools <br>- Streaming<br>- Text(input/output)<br>- Image(input) | 128,000 | 16,384 | Oct 2023 |
114+
| `gpt-4.5-preview` (2025-02-27) <br> **GPT-4.5 Preview** | [GPT 4.1](#gpt-41-series) is the recommended replacement for this model. Excels at diverse text and image tasks. <br>- Structured outputs <br>- Prompt caching <br>- Tools <br>- Streaming<br>- Text(input/output)<br>- Image(input) | 128,000 | 16,384 | October 2023 |
115115

116116
> [!NOTE]
117117
> It is expected behavior that the model cannot answer questions about itself. If you want to know when the knowledge cutoff for the model's training data is, or other details about the model you should refer to the model documentation above.
@@ -126,10 +126,10 @@ The Azure OpenAI o<sup>&#42;</sup> series models are specifically designed to ta
126126
| `o3-pro` (2025-06-10) | - [Responses API](../how-to/responses.md) <br>- Structured outputs<br> - Text, image processing <br> - Functions/Tools<br> [Full summary of capabilities](../how-to/reasoning.md) | Input: 200,000 <br> Output: 100,000 | May 31, 2024 |
127127
| `o4-mini` (2025-04-16) | - **NEW** reasoning model, offering [enhanced reasoning abilities](../how-to/reasoning.md). <br><br> - Chat Completions API <br> - [Responses API](../how-to/responses.md) <br>- Structured outputs<br> - Text, image processing <br> - Functions/Tools<br> [Full summary of capabilities](../how-to/reasoning.md) | Input: 200,000 <br> Output: 100,000 | May 31, 2024 |
128128
| `o3` (2025-04-16) | - **NEW** reasoning model, offering [enhanced reasoning abilities](../how-to/reasoning.md). <br> <br> - Chat Completions API <br> - [Responses API](../how-to/responses.md) <br> - Structured outputs<br> - Text, image processing <br> - Functions/Tools/Parallel tool calling <br> [Full summary of capabilities](../how-to/reasoning.md) | Input: 200,000 <br> Output: 100,000 | May 31, 2024 |
129-
| `o3-mini` (2025-01-31) | - [Enhanced reasoning abilities](../how-to/reasoning.md). <br> - Structured outputs<br> - Text-only processing <br> - Functions/Tools | Input: 200,000 <br> Output: 100,000 | Oct 2023 |
130-
| `o1` (2024-12-17) | - [Enhanced reasoning abilities](../how-to/reasoning.md). <br> - Structured outputs<br> - Text, image processing <br> - Functions/Tools | Input: 200,000 <br> Output: 100,000 | Oct 2023 |
131-
|`o1-preview` (2024-09-12) | Older preview version | Input: 128,000 <br> Output: 32,768 | Oct 2023 |
132-
| `o1-mini` (2024-09-12) | A faster and more cost-efficient option in the o1 series, ideal for coding tasks requiring speed and lower resource consumption. <br><br> Global standard deployment available by default. <br> <br> Standard (regional) deployments are currently only available for select customers who received access as part of the `o1-preview` limited access release. | Input: 128,000 <br> Output: 65,536 | Oct 2023 |
129+
| `o3-mini` (2025-01-31) | - [Enhanced reasoning abilities](../how-to/reasoning.md). <br> - Structured outputs<br> - Text-only processing <br> - Functions/Tools | Input: 200,000 <br> Output: 100,000 | October 2023 |
130+
| `o1` (2024-12-17) | - [Enhanced reasoning abilities](../how-to/reasoning.md). <br> - Structured outputs<br> - Text, image processing <br> - Functions/Tools | Input: 200,000 <br> Output: 100,000 | October 2023 |
131+
|`o1-preview` (2024-09-12) | Older preview version | Input: 128,000 <br> Output: 32,768 | October 2023 |
132+
| `o1-mini` (2024-09-12) | A faster and more cost-efficient option in the o1 series, ideal for coding tasks requiring speed and lower resource consumption. <br><br> Global standard deployment available by default. <br> <br> Standard (regional) deployments are currently only available for select customers who received access as part of the `o1-preview` limited access release. | Input: 128,000 <br> Output: 65,536 | October 2023 |
133133

134134
### Availability
135135

@@ -187,10 +187,10 @@ See [model versions](../concepts/model-versions.md) to learn about how Azure Ope
187187

188188
| Model ID | Description | Max Request (tokens) | Training Data (up to) |
189189
| --- | :--- |:--- |:---: |
190-
| `gpt-4o` (2024-11-20) <br> **GPT-4o (Omni)** | **Latest large GA model** <br> - Structured outputs<br> - Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks. <br> - **Enhanced creative writing ability** | Input: 128,000 <br> Output: 16,384 | Oct 2023 |
191-
|`gpt-4o` (2024-08-06) <br> **GPT-4o (Omni)** | - Structured outputs<br> - Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks |Input: 128,000 <br> Output: 16,384 | Oct 2023 |
192-
|`gpt-4o-mini` (2024-07-18) <br> **GPT-4o mini** | **Latest small GA model** <br> - Fast, inexpensive, capable model ideal for replacing GPT-3.5 Turbo series models. <br> - Text, image processing <br>- JSON Mode <br> - parallel function calling | Input: 128,000 <br> Output: 16,384 | Oct 2023 |
193-
|`gpt-4o` (2024-05-13) <br> **GPT-4o (Omni)** | Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks |Input: 128,000 <br> Output: 4,096| Oct 2023 |
190+
| `gpt-4o` (2024-11-20) <br> **GPT-4o (Omni)** | **Latest large GA model** <br> - Structured outputs<br> - Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks. <br> - **Enhanced creative writing ability** | Input: 128,000 <br> Output: 16,384 | October 2023 |
191+
|`gpt-4o` (2024-08-06) <br> **GPT-4o (Omni)** | - Structured outputs<br> - Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks |Input: 128,000 <br> Output: 16,384 | October 2023 |
192+
|`gpt-4o-mini` (2024-07-18) <br> **GPT-4o mini** | **Latest small GA model** <br> - Fast, inexpensive, capable model ideal for replacing GPT-3.5 Turbo series models. <br> - Text, image processing <br>- JSON Mode <br> - parallel function calling | Input: 128,000 <br> Output: 16,384 | October 2023 |
193+
|`gpt-4o` (2024-05-13) <br> **GPT-4o (Omni)** | Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks |Input: 128,000 <br> Output: 4,096| October 2023 |
194194
| `gpt-4` (turbo-2024-04-09) <br>**GPT-4 Turbo with Vision** | **New GA model** <br> - Replacement for all previous GPT-4 preview models (`vision-preview`, `1106-Preview`, `0125-Preview`). <br> - [**Feature availability**](#gpt-4o-and-gpt-4-turbo) is currently different depending on method of input, and deployment type. | Input: 128,000 <br> Output: 4,096 | Dec 2023 |
195195
| `gpt-4-32k` (0613) | **Older GA model** <br> - Basic function calling with tools | 32,768 | Sep 2021 |
196196
| `gpt-4` (0613) | **Older GA model** <br> - Basic function calling with tools | 8,192 | Sep 2021 |
@@ -281,11 +281,11 @@ Details about maximum request tokens and training data are available in the foll
281281

282282
| Model ID | Description | Max Request (tokens) | Training Data (up to) |
283283
|---|---|---|---|
284-
|`gpt-4o-mini-audio-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for audio and text generation. |Input: 128,000 <br> Output: 4,096 | Oct 2023 |
285-
|`gpt-4o-mini-realtime-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for real-time audio processing. |Input: 128,000 <br> Output: 4,096 | Oct 2023 |
286-
|`gpt-4o-audio-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for audio and text generation. |Input: 128,000 <br> Output: 4,096 | Oct 2023 |
287-
|`gpt-4o-realtime-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for real-time audio processing. |Input: 128,000 <br> Output: 4,096 | Oct 2023 |
288-
|`gpt-4o-mini-realtime-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for real-time audio processing. |Input: 128,000 <br> Output: 4,096 | Oct 2023 |
284+
|`gpt-4o-mini-audio-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for audio and text generation. |Input: 128,000 <br> Output: 16,384 | September 2023 |
285+
|`gpt-4o-audio-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for audio and text generation. |Input: 128,000 <br> Output: 16,384 | September 2023 |
286+
|`gpt-4o-realtime-preview` (2025-06-03) <br> **GPT-4o audio** | **Audio model** for real-time audio processing. |Input: 128,000 <br> Output: 4,096 | October 2023 |
287+
|`gpt-4o-realtime-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for real-time audio processing. |Input: 128,000 <br> Output: 4,096 | October 2023 |
288+
|`gpt-4o-mini-realtime-preview` (2024-12-17) <br> **GPT-4o audio** | **Audio model** for real-time audio processing. |Input: 128,000 <br> Output: 4,096 | October 2023 |
289289

290290
To compare the availability of GPT-4o audio models across all regions, see the [models table](#global-standard-model-availability).
291291

0 commit comments

Comments
 (0)