DALL-E 3

OpenAI o3

OpenAI's most powerful reasoning model, pushing the frontier across coding, math, science, and visual perception. Trained to think longer before responding and agentically use tools (web search, code execution, image generation) to solve complex problems. Sets new SOTA on benchmarks like Codeforces and MMMU.

OpenAI o4-mini

A smaller, cost-efficient reasoning model from OpenAI optimized for speed. Achieves remarkable performance for its size, particularly in math, coding, and visual tasks. Supports significantly higher usage limits than o3 and can agentically use tools.

OpenAI o4 Mini High

OpenAI o4-mini-high is the same model as o4-mini but defaults to a high reasoning effort setting. It's a compact reasoning model optimized for speed and cost-efficiency, retaining strong multimodal and agentic capabilities, especially in math, coding, and visual tasks.

GPT-4o (Omni)

GPT-4o processes text, images, and audio through a unified transformer architecture and offers real-time translation for 154 languages with 89.2% BLEU score on low-resource languages.

GPT-4.1

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.

o3 Mini

o3 Mini is a smaller, more efficient version of the o3 model, optimized for faster response times and lower computational costs while maintaining high-quality outputs.

o1

o1 achieves 86% accuracy on Mathematics Olympiad benchmarks (vs. GPT-4o's 13%), offers PhD-level STEM proficiency, and maintains a 0.17% deceptive response rate in synthetic testing.

GPT-4.5

GPT-4.5 is a step forward in scaling up pre-training and post-training. With broader knowledge, improved intent understanding, and greater 'EQ', it excels at natural conversations, writing, programming, and practical problem solving with reduced hallucinations. GPT-4.5 achieved 62.5% accuracy on SimpleQA and a 37.1% hallucination rate, significantly outperforming GPT-4o and other models.

ChatGPT-4o (March 2025)

An updated version of GPT-4o that feels more intuitive, creative, and collaborative. Follows instructions more accurately, handles coding tasks more smoothly, and communicates in a clearer, more natural way with more concise responses and fewer markdown levels.

GPT-4o mini

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.

GPT-4.1 Nano

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It's ideal for tasks like classification or autocompletion.

GPT-4.1 Mini

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider's polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.

GPT-3.5 Turbo

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.

GPT-4

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.

GPT-2

A direct scale-up of GPT-1 with 1.5 billion parameters, trained on 8 million web pages. Known for its ability to generate coherent text, sometimes indistinguishable from humans, but could be repetitive.

GPT-1

The first large-scale transformer-based language model released by OpenAI, trained on the BooksCorpus dataset. This version is accessed via the Hugging Face model hub (`openai-community/openai-gpt`).

OpenAI Codex Mini

codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.

GPT OSS 20B

OpenAI's efficient open-weight model featuring 21B parameters with MoE architecture, optimized for edge deployment and consumer hardware. Matches o3-mini performance while requiring only 16GB memory, making it ideal for on-device AI applications.

GPT OSS 120B

OpenAI's first open-weight model since GPT-2, featuring 117B parameters with MoE architecture. Designed for high-reasoning, agentic, and general-purpose production use cases with configurable reasoning depth and native tool use.

GPT-5

OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. Optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. Supports test-time routing and advanced prompt understanding (e.g., "think hard about this"). Reductions in hallucination/sycophancy with better performance in coding, writing, and health-related tasks.

GPT-5 Pro

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. Optimized for complex, high-stakes tasks that demand step-by-step reasoning, instruction following, and accuracy. Supports test-time routing controls and advanced prompt understanding, including intent cues like "think hard about this". Delivers reduced hallucination, lower sycophancy, and stronger performance across coding, writing, and health-related workloads.

GPT-5 Mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model. Context window: 400,000 tokens.

GPT-5 Nano

GPT-5 Nano model integrated via automation on 2025-08-07

GPT-5 Codex

GPT-5 Codex model integrated via automation on 2025-09-23

GPT-5.1

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.

GPT-5.1 Chat

GPT-5.1 Chat (AKA Instant) is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively think on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations.

GPT-5.1-Codex-Mini

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex, optimized for coding tasks with lower latency while maintaining strong code generation capabilities.

GPT-5.1-Codex

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks including building projects from scratch, feature development, debugging, large-scale refactoring, and code review.