gpt-5-codex
Version: 2025-09-15
Key Capabilities
gpt‑5‑codex is a multimodal, repo-aware coding model built on the gpt‑5 architecture, designed to deliver intelligent, context-rich assistance across IDEs, terminals, and browser-based environments. Whether you're reviewing code, automating builds, gpt‑5‑codex brings deep reasoning, seamless tool integration, and visual feedback to your development workflow. Why gpt‑5‑codex? a. Multimodal reasoning: Accepts both text and image inputs—ideal for reasoning across code, UI states, architecture diagrams, and design comps in single workflow. b. Context-aware code reviews: Surfaces critical flows and quality issues with AI-powered insights into your development surfaces. c. Asynchronous execution: Supports long-running tasks with model-guided loops that retain state and context across interactions. d. Repo-aware intelligence: Understands full repositories, enabling cohesive refactors, test automation, and visual verification via screenshots.Model Variants
gpt-5-codex: This is the most advanced coding model in the gpt‑5 family.
Key Capabilities
gpt‑5‑codex supports features such as streaming, function calling, structured outputs, and image input/output. With these capabilities, developers can leverage gpt‑5‑codex for a wide range of intelligent, multimodal development tasks. For developers seeking smarter, safer, and more integrated AI assistance, this model offers a powerful new tool in your AI toolkit.Model provider
This model is provided through the Azure OpenAI Service.Relevant documents
The following documents are applicable:- Overview of Responsible AI practices for Azure OpenAI models
- Transparency Note for Azure OpenAI Service
Content Filtering
Prompts and completions are passed through a default configuration of Azure AI Content Safety classification models to detect and prevent the output of harmful content. Learn more about Azure AI Content Safety . Additional classification models and configuration options are available when you deploy an Azure OpenAI model in production; learn more .Model Specifications
Context Length272000
LicenseCustom
Training DataOctober 2024
Last UpdatedSeptember 2025
Input TypeText,Image
Output TypeText
PublisherOpenAI
Languages1 Language