GPT-5 Nano is OpenAI's fastest, cheapest version of GPT-5. It's great for summarization and classification tasks
The company that provides the model
The number of tokens you can send in a prompt
The maximum number of tokens a model can generate in one request
The cost of prompt tokens sent to the model
The cost of output tokens generated by the model
When the model's knowledge ends
When the model was launched
Capability for the model to use external tools
Ability to process and analyze visual inputs, like images
Support for multiple languages
Whether the model supports fine-tuning on custom datasets
GPT-5 Nano is OpenAI’s fastest, most cost-effective variant of GPT-5, optimized for tasks like summarization and classification.
It costs $0.05 per million tokens (input and output combined can be treated under this rate) and $0.40 per million output tokens if billed separately.
GPT-5 Nano supports a context window of up to 400,000 tokens.
It can generate up to 128,000 tokens in a single response.
GPT-5 Nano was released on August 7, 2025.
Its knowledge cut-off date is May 30, 2024.
Yes, GPT-5 Nano supports multimodal inputs, including images.
Yes, it supports function calling and integration with external tools.
Yes, it handles multiple languages for both input and output.
Yes, GPT-5 Nano supports fine-tuning.
You can find more information here.
Collaborate with thousands of AI builders to discover, manage, and improve prompts—free to get started.
