AI Model Lineup

Offering diverse AI model options to meet different scenarios and performance needs

Basic Series

GPT-5

OpenAI's fifth-generation large language model, achieving major breakthroughs in comprehension, reasoning, and creativity. Ideal for complex task processing and advanced conversational scenarios.

Supported Depths:LowMediumHigh

GPT-5.1

Enhanced version of GPT-5 with significantly improved performance and response speed. Optimized context understanding and multi-turn conversation capabilities provide users with a smoother interactive experience.

Supported Depths:LowMediumHigh

GPT-5.2

Latest version of the GPT-5 series with knowledge cutoff updated to August 31, 2025. Features a 400k token context window and 128k maximum output tokens, reaching new heights in reasoning capability and performance.

Supported Depths:LowMediumHighxhigh

Codex Code-Specialized Series

GPT-5-Codex

GPT-5 version optimized specifically for code generation and programming tasks. Excels in code completion, debugging, refactoring, and technical documentation writing, serving as a powerful assistant for developers.

Supported Depths:LowMediumHigh

GPT-5.1-Codex

Upgraded code-specialized model with further improvements in code understanding and generation quality. Supports more programming languages and frameworks, with deeper understanding of complex project structures and architectural patterns.

Supported Depths:LowMediumHigh

GPT-5.2-Codex

Code-specialized model built for demanding software engineering and defensive cybersecurity tasks, released on December 18, 2025. Compared to GPT-5.1-Codex, it offers significant improvements in context compaction, massive code refactors and migrations, Windows environment compatibility, and cybersecurity defense capabilities, setting a new industry benchmark for agentic coding.

Supported Depths:LowMediumHighxhigh

Codex Mini Lightweight Series

GPT-5-Codex-Mini

Lightweight code model that maintains high-quality code generation while significantly improving response speed and performance efficiency. Ideal for quick code completion and real-time programming assistance scenarios.

Supported Depths:LowMediumHigh

GPT-5.1-Codex-Mini

Optimized lightweight code model combining GPT-5.1's performance improvements with Mini series efficiency. Achieves ideal balance between speed and quality, perfect for daily development work.

Supported Depths:LowMediumHigh

Codex Max Flagship Series

GPT-5.1-Codex-Max

Flagship code model providing the most powerful code understanding and generation capabilities. Supports extra-high depth reasoning and can handle the most complex software engineering tasks, including large-scale system architecture design and performance optimization.

Supported Depths:LowMediumHighxhigh
支持的模型 - CodexZH | GPT-5, GPT-5.1, GPT-5.2, Codex 全系列模型