OpenAI's GPT-5-CODEX is a chat model capable of various tasks, including code completion, generation, and review, as well as reasoning and tool use. It excels in mathematical reasoning, with a top 10% score on the Math Index, and also performs well in coding tasks, as evidenced by its top 25% scores on the Coding Index and LiveCodeBench.
Input
Output
Context
272K
Max Output
128K
Parameters
-
Input Modalities
Output Modalities
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.