Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.
Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models .

Key capabilities

About this model

As measured on traditional benchmarks, gpt-4o achieves gpt-4 turbo-level performance on text, reasoning, and coding intelligence, while setting new high watermarks on multilingual, audio, and vision capabilities.

Key model capabilities

Text, image processing
JSON Mode
parallel function calling
Enhanced accuracy and responsiveness
Parity with English text and coding tasks compared to GPT-4 Turbo with Vision
Superior performance in non-English languages and in vision tasks
Support for enhancements
Support for complex structured outputs.

Model	MMLU	GPQA	MATH	MGSM	DROP	HumanEval
GPT-4o (2024-08-06)	88.7	53.6	76.6	90.5	83.4	90.2
GPT-4T	86.5	48.0	72.6	88.5	86.0	87.1
GPT-4	86.4	35.7	42.5	74.5	80.9	67.0
Claude3 Opus	86.8	50.4	60.1	90.7	83.1	84.9
Gemini Pro 1.5	81.9	--	58.5	88.7	78.9	71.9
Gemini Ultra 1.0	83.7	--	53.2	79.0	82.4	74.4
Llama3 400b	86.1	48.0	57.8	--	83.5	84.1

Source: the OpenAI announcement .

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The introduction of gpt-4o opens numerous possibilities for businesses in various sectors:

Enhanced customer service: By integrating diverse data inputs, gpt-4o enables more dynamic and comprehensive customer support interactions.
Advanced analytics: Leverage gpt-4o's capability to process and analyze different types of data to enhance decision-making and uncover deeper insights.
Content innovation: Use gpt-4o's generative capabilities to create engaging and diverse content formats, catering to a broad range of consumer preferences.

Out of scope use cases

We recognize that gpt-4o's audio modalities present a variety of novel risks. Today we are publicly releasing text and image inputs and text outputs. Over the upcoming weeks and months, we'll be working on the technical infrastructure, usability via post-training, and safety necessary to release the other modalities. For example, at launch, audio outputs will be limited to a selection of preset voices and will abide by our existing safety policies.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Text, image processing

Output formats

Text outputs, JSON Mode, parallel function calling, Support for complex structured outputs.

Supported languages

Superior performance in non-English languages

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

Supports all previous output size (16,384)

Optimizing model performance

The provider has not supplied this information.

Additional assets

Training disclosure

Training, testing and validation

gpt-4o has safety built-in by design across modalities, through techniques such as filtering training data and refining the model's behavior through post-training.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The following documents are applicable:

We have also created new safety systems to provide guardrails on voice outputs. We've evaluated gpt-4o according to our Preparedness Framework and in line with our voluntary commitments . Our evaluations of cybersecurity, CBRN, persuasion, and model autonomy show that GPT-4o does not score above Medium risk in any of these categories. This assessment involved running a suite of automated and human evaluations throughout the model training process. We tested both pre-safety-mitigation and post-safety-mitigation versions of the model, using custom fine-tuning and prompts, to better elicit model capabilities. gpt-4o has also undergone extensive external red teaming with 70+ external experts in domains such as social psychology, bias and fairness, and misinformation to identify risks that are introduced or amplified by the newly added modalities. We used these learnings to build out our safety interventions in order to improve the safety of interacting with GPT-4o. We will continue to mitigate new risks as they're discovered. Prompts and completions are passed through a default configuration of Azure AI Content Safety classification models to detect and prevent the output of harmful content. Learn more about Azure AI Content Safety . Additional classification models and configuration options are available when you deploy an Azure OpenAI model in production; learn more .

Responsible AI considerations

Safety techniques

gpt-4o has safety built-in by design across modalities, through techniques such as filtering training data and refining the model's behavior through post-training. We have also created new safety systems to provide guardrails on voice outputs. Prompts and completions are passed through a default configuration of Azure AI Content Safety classification models to detect and prevent the output of harmful content. Learn more about Azure AI Content Safety . Additional classification models and configuration options are available when you deploy an Azure OpenAI model in production; learn more .

Safety evaluations

We've evaluated gpt-4o according to our Preparedness Framework and in line with our voluntary commitments . Our evaluations of cybersecurity, CBRN, persuasion, and model autonomy show that GPT-4o does not score above Medium risk in any of these categories. This assessment involved running a suite of automated and human evaluations throughout the model training process. We tested both pre-safety-mitigation and post-safety-mitigation versions of the model, using custom fine-tuning and prompts, to better elicit model capabilities. gpt-4o has also undergone extensive external red teaming with 70+ external experts in domains such as social psychology, bias and fairness, and misinformation to identify risks that are introduced or amplified by the newly added modalities. We used these learnings to build out our safety interventions in order to improve the safety of interacting with GPT-4o. We will continue to mitigate new risks as they're discovered.

Known limitations

We recognize that gpt-4o's audio modalities present a variety of novel risks. Today we are publicly releasing text and image inputs and text outputs. Over the upcoming weeks and months, we'll be working on the technical infrastructure, usability via post-training, and safety necessary to release the other modalities. For example, at launch, audio outputs will be limited to a selection of preset voices and will abide by our existing safety policies.

Acceptable use

Acceptable use policy

The provider has not supplied this information.

Quality and performance evaluations

Source: OpenAI As measured on traditional benchmarks, gpt-4o achieves gpt-4 turbo-level performance on text, reasoning, and coding intelligence, while setting new high watermarks on multilingual, audio, and vision capabilities.

Model	MMLU	GPQA	MATH	MGSM	DROP	HumanEval
GPT-4o (2024-08-06)	88.7	53.6	76.6	90.5	83.4	90.2
GPT-4T	86.5	48.0	72.6	88.5	86.0	87.1
GPT-4	86.4	35.7	42.5	74.5	80.9	67.0
Claude3 Opus	86.8	50.4	60.1	90.7	83.1	84.9
Gemini Pro 1.5	81.9	--	58.5	88.7	78.9	71.9
Gemini Ultra 1.0	83.7	--	53.2	79.0	82.4	74.4
Llama3 400b	86.1	48.0	57.8	--	83.5	84.1

We've evaluated gpt-4o according to our Preparedness Framework and in line with our voluntary commitments . Our evaluations of cybersecurity, CBRN, persuasion, and model autonomy show that GPT-4o does not score above Medium risk in any of these categories. This assessment involved running a suite of automated and human evaluations throughout the model training process. We tested both pre-safety-mitigation and post-safety-mitigation versions of the model, using custom fine-tuning and prompts, to better elicit model capabilities. gpt-4o has also undergone extensive external red teaming with 70+ external experts in domains such as social psychology, bias and fairness, and misinformation to identify risks that are introduced or amplified by the newly added modalities. We used these learnings to build out our safety interventions in order to improve the safety of interacting with GPT-4o. We will continue to mitigate new risks as they're discovered.

Benchmarking methodology

Source: OpenAI The provider has not supplied this information.

Public data summary

Source: OpenAI The provider has not supplied this information.