GPT-5.5

GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.

GPT Image 2

OpenAI's second-generation image model. Near-perfect typography (including non-Latin scripts), 2x faster than gpt-image-1.5, up to 2K resolution, and 'thinking' over the prompt for dense compositions.

GPT-5.3 Chat

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly reduces unnecessary refusals, caveats, and overly cautious phrasing that can interrupt conversational flow. The model is more willing to engage with nuanced topics, produces cleaner and more natural prose, and maintains strong performance across reasoning, coding, and creative tasks while feeling less robotic in casual interaction.

GPT-5.3-Codex

GPT-5.3-Codex is OpenAI's most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.

GPT Image 1.5

OpenAI's latest image generation model with strong instruction following, optional transparent backgrounds, and quality controls.

GPT Image 1.5 (Low)

GPT Image 1.5 with `quality=low` for faster and cheaper generations.

GPT-5.5

GPT-5.5 is OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.

GPT Image 2

OpenAI's second-generation image model. Near-perfect typography (including non-Latin scripts), 2x faster than gpt-image-1.5, up to 2K resolution, and 'thinking' over the prompt for dense compositions.

GPT-5.3 Chat

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly reduces unnecessary refusals, caveats, and overly cautious phrasing that can interrupt conversational flow. The model is more willing to engage with nuanced topics, produces cleaner and more natural prose, and maintains strong performance across reasoning, coding, and creative tasks while feeling less robotic in casual interaction.

GPT-5.3-Codex

GPT-5.3-Codex is OpenAI's most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.

GPT Image 1.5

OpenAI's latest image generation model with strong instruction following, optional transparent backgrounds, and quality controls.

GPT Image 1.5 (Low)

GPT Image 1.5 with `quality=low` for faster and cheaper generations.