OpenAI's new o3, o4-mini, GPT-4.1 models

Orq.ai now supports the latest OpenAI models: o3, o4-mini, GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano.

o3

OpenAI’s most advanced reasoning model, o3 excels in complex tasks across math, science, and coding. It integrates visual inputs into its reasoning process, enabling functionalities like interpreting sketches or whiteboards. o3 also supports comprehensive tool usage, including web browsing, Python execution, and file analysis.   

o4-mini

A compact reasoning model optimized for speed and cost-efficiency, o4-mini delivers strong performance in math, coding, and visual tasks. It supports a 200,000-token context window and up to 100,000 output tokens, making it suitable for high-throughput applications.  

GPT-4.1 Series

• GPT-4.1: Enhanced coding capabilities, improved instruction following, and support for up to 1 million tokens of context. It outperforms previous models on coding benchmarks and is optimized for real-world applications.
• GPT-4.1 mini: Balances performance and efficiency, inheriting core strengths of the GPT-4.1 series, including enhanced coding and long-context understanding.
• GPT-4.1 nano: The fastest and most cost-effective model in the GPT-4.1 series, ideal for tasks requiring low latency, such as classification or autocompletion. It maintains a 1 million-token context window.