OpenAI

OpenAI's Codex CLI is a local coding agent that reads, modifies, and runs code through natural language commands. Enables building, debugging, and automating coding tasks.

Codex App is OpenAI's desktop command center for running coding agents in parallel, reviewing changes, using worktrees, and sharing sessions with Codex CLI and IDE integrations.

OpenAI's Codex is an AI coding assistant extension for your IDE. It reads, modifies, and runs code through natural language commands, enabling building, debugging, and automating coding tasks.

GPT-4.1 mini

Smaller GPT-4.1 model for efficient instruction following, long-context code work, and tool-driven applications.

GPT-4.1 nano

Smallest GPT-4.1 model, optimized for high-volume classification, extraction, code-adjacent automation, and low latency.

GPT-4.1

Released in April 2025, GPT-4.1 shows particularly significant improvements in coding and frontend web development, featuring 1M token context window for complex coding tasks.

GPT-4o mini

Fast, affordable GPT-4o variant for focused tasks, including code generation and structured tool workflows.

GPT-4o

OpenAI's flagship multimodal model optimized for coding tasks, featuring 128K context window and advanced reasoning capabilities for code generation and debugging.

GPT-5.1-Codex-Max

Long-horizon Codex model optimized for project-scale refactoring, persistent execution, and large software tasks.

GPT-5.1-Codex mini

Smaller and more cost-effective GPT-5.1-Codex variant for agentic coding workloads.

GPT-5.1-Codex

GPT-5.1 optimized for software engineering. Supports interactive development, complex tasks, building projects, feature development, debugging, refactoring, and code review.

GPT-5.1

Latest GPT-5 series model with stronger reasoning and natural conversation. Uses adaptive reasoning to respond quickly to simple queries while providing depth for complex tasks.

GPT-5.2-Codex

GPT-5.2 variant optimized for long-horizon agentic coding, code review, and software engineering workflows.

GPT-5.2 Pro

High-compute GPT-5.2 variant for complex professional reasoning and software engineering work.

GPT-5.2

OpenAI's new generation high-performance model, building upon GPT-5.1 with enhanced reasoning capabilities, larger context understanding, and improved coding performance features.

GPT-5.3-Codex

OpenAI's agentic coding model for long-running software engineering, research, tool use, and complex computer-based work.

GPT-5.4 mini

OpenAI's fast and efficient GPT-5.4 model for coding, computer use, multimodal understanding, tool use, and subagent workloads.

GPT-5.4 nano

OpenAI's smallest GPT-5.4 model for high-volume classification, extraction, ranking, multimodal tasks, and simpler coding subagents.

GPT-5.4 Pro

OpenAI's higher-compute GPT-5.4 variant for difficult coding, reasoning, agentic, and professional tasks requiring more precise answers.

GPT-5.4

OpenAI's frontier model for complex professional work, including coding, tool use, computer operation, and long-context workflows.

GPT-5.5 Pro

OpenAI's higher-compute GPT-5.5 variant for difficult coding, reasoning, agentic, and professional tasks requiring more precise answers.

GPT-5.5

OpenAI's frontier model for agentic coding, computer use, knowledge work, scientific research, and complex multi-tool tasks.

GPT-5.6 Luna

OpenAI's fastest and most cost-efficient GPT-5.6 model, designed for cost-sensitive, high-volume professional workloads.

GPT-5.6 Sol

OpenAI's flagship GPT-5.6 model for complex professional work across coding, research, science, cybersecurity, computer use, and design.

GPT-5.6 Terra

OpenAI's balanced GPT-5.6 model for everyday professional work, combining high intelligence with lower cost than the flagship Sol tier.

GPT-5 Codex

GPT-5 optimized for software engineering. Supports interactive development, complex tasks, building projects, feature development, debugging, refactoring, and code review.

GPT-5 mini

Cost-efficient GPT-5 variant for precise, well-defined coding and high-volume agent tasks.

GPT-5 nano

Smallest GPT-5 variant for low-latency coding utilities, classification, extraction, and automation.

GPT-5 Pro

High-compute GPT-5 variant for difficult professional reasoning and software engineering work.

GPT-5

OpenAI's most advanced model with major improvements in reasoning, code quality, and UX. Optimized for complex tasks requiring step-by-step reasoning and high accuracy.

o3-mini

Compact reasoning model optimized for coding, mathematics, and science with configurable reasoning effort.

o3

Reasoning model for complex coding, mathematics, science, and visual analysis tasks.

o4-mini

Fast reasoning model for coding, mathematics, and visual problem solving with efficient tool use.