OpenAI o1-mini

GPT-5 is our flagship model for coding, reasoning, and agentic tasks across domains. The best model for coding and agentic tasks with higher reasoning capabilities.

GPT-5 mini is a faster, more cost-efficient version of GPT-5. Great for well-defined tasks and precise prompts with high reasoning capabilities.

GPT-5 nano is our fastest, cheapest version of GPT-5. Great for summarization and classification tasks with average reasoning capabilities.

GPT model for web search in Chat Completions. High performance model trained to understand and execute web search queries with additional per-tool-call fees. No function calling support.

Fast, affordable small model for web search. Specialized for web search in Chat Completions with additional per-tool-call fees. No function calling support.

o4-mini is OpenAI’s new reasoning model that supports image and text inputs and generates text outputs. It is suitable for complex tasks requiring broad general knowledge. The model has a 200K token context window and a knowledge cutoff of May 31, 2024.

o3 is OpenAI’s new reasoning model that supports image and text inputs and generates text outputs. It is suitable for complex tasks requiring broad general knowledge. The model has a 200K token context window and a knowledge cutoff of May 31, 2024.

o1 is OpenAI's new reasoning model, suitable for complex tasks that require extensive general knowledge. This model features a 128K context and has a knowledge cutoff date of October 2023.