OpenAI gpt-5-nano
Version: 2025-08-07
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.
Key capabilities
About this model
gpt-5-nano is a new class of reasoning model focuses on speed and efficiency with reasoning power for rich question and responses.Key model capabilities
- Supports ultra-fast, low-latency use cases
- Now supporting minimal reasoning, a new verbosity setting, and the "customs" tool for raw text output.
- New "allowed tools" tool choice that enables you to specify multiple tools in the tool choice instead of just one
- New "preamble" support, allowing the model to "think" before calling a tool. This is always enabled and controlled through prompting.
- gpt-5-nano supports multimodal inputs, real-time streaming and full tool support for smarter, more dynamic user experiences
Use cases
See Responsible AI for additional considerations for responsible use.Key use cases
Optimized for speed, ideal for applications requiring low latency.Out of scope use cases
The provider has not supplied this information.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
gpt-5-nano supports multimodal inputs, real-time streaming and full tool support for smarter, more dynamic user experiencesOutput formats
Now supporting minimal reasoning, a new verbosity setting, and the "customs" tool for raw text output.Supported languages
The provider has not supplied this information.Sample JSON response
The provider has not supplied this information.Model architecture
The provider has not supplied this information.Long context
The provider has not supplied this information.Optimizing model performance
The provider has not supplied this information.Additional assets
The provider has not supplied this information.Training disclosure
Training, testing and validation
The provider has not supplied this information.Distribution
Distribution channels
This model is provided through the Azure OpenAI Service.More information
The following documents are applicable:- Overview of Responsible AI practices for Azure OpenAI models
- Transparency Note for Azure OpenAI Service
Responsible AI considerations
Safety techniques
OpenAI has incorporated additional safety measures including new techniques to help the models refuse unsafe requests. These advancements make the gpt-5 series some of the most robust models available.Safety evaluations
OpenAI measures safety by testing how well models continue to follow its safety rules if a user tries to bypass them (known as "jailbreaking"). In OpenAI's internal tests, GPT-4o scored 22 (on a scale of 0-100) while o1-preview model scored 84. You can read more about this in the OpenAI's system card and research post .Known limitations
The provider has not supplied this information.Acceptable use
Acceptable use policy
The provider has not supplied this information.Quality and performance evaluations
Source: OpenAI The provider has not supplied this information.Benchmarking methodology
Source: OpenAI The provider has not supplied this information.Public data summary
Source: OpenAI OpenAI measures safety by testing how well models continue to follow its safety rules if a user tries to bypass them (known as "jailbreaking"). In OpenAI's internal tests, GPT-4o scored 22 (on a scale of 0-100) while o1-preview model scored 84. You can read more about this in the OpenAI's system card and research post .Model Specifications
Context Length200000
Quality Index0.83
LicenseCustom
Training DataMay 2024
Last UpdatedDecember 2025
Input TypeText,Image
Output TypeText
ProviderOpenAI
Languages1 Language
Related Models
