Base44
Mini toolsGPT models
Browse all models from this model family.
to
-
By OpenAIGPT-5.2-Codex is OpenAI’s frontier agentic coding model based on GPT-5.2, optimized for long-horizon software work, large refactors and migrations, better Windows support and state-of-the-art cybersecurity performance in Codex.NewCodingReleased 13d ago
-
By OpenAIGPT-5.3-Codex is OpenAI’s most capable agentic coding model, combining GPT-5.2-Codex’s frontier coding with GPT-5.2’s reasoning in one model that is ~25% faster, tops SWE-Bench Pro and Terminal-Bench, and runs long, tool-using workflows on a computer.NewCodingReleased 13d ago
-
By OpenAIGPT Image 1.5 is OpenAI’s new flagship text to image model behind ChatGPT Images, offering more precise edits, better instruction following and text rendering, and up to 4x faster generation while preserving composition, lighting and facial likeness.NewImageReleased 2mo ago
-
By OpenAIGPT-5.2 Pro is the highest-end 5.2 model, tuned for difficult scientific, mathematical and coding problems, offering the strongest accuracy and reasoning when quality matters more than speed.NewMultimodalReleased 2mo ago
-
By OpenAIGPT-5.2 Thinking is the deeper reasoning variant, designed for complex professional tasks like coding, long-document analysis, planning and math, trading speed for stronger multi-step logic and reliability.NewMultimodalReleased 2mo ago
-
By OpenAIGPT-5.2 Instant is the fast, lower-latency member of the 5.2 family, built for everyday Q&A, how-tos, research and writing where quick answers matter more than maximum depth of reasoning.NewMultimodalReleased 2mo ago
-
NewMultimodalReleased 2mo ago
-
By OpenAIGPT 5.1 Codex High trades a bit of speed for higher accuracy on complex coding tasks. It performs deeper reasoning, stronger spec adherence, and safer edits with the same long context and tool calling surface.MultimodalReleased 3mo ago
-
By OpenAIGPT 5.1 Codex is a code-focused variant that maps specs to working code, writes diffs and tests, and understands repositories with long context, tool calling, and strict JSON or patch output.MultimodalReleased 3mo ago
-
By OpenAIGPT-Image-1 is OpenAI’s text-to-image and edit model for prompt fidelity, readable typography, and on-canvas edits.NewImageReleased 2mo ago
-
By OpenAIo4-mini-high is the higher-accuracy profile of the mini line. It trades a bit of speed for stronger reasoning and coding, with long context, tool and function calling, streaming, and reliable JSON.TextReleased 10mo ago
-
TextReleased 10mo ago
-
By OpenAIGPT-5.1 upgrades GPT-5 with two models, Instant and Thinking. Instant is warmer and more conversational, now with adaptive reasoning for harder prompts and better instruction following. Thinking adapts its thinking time per task and writes clearer, easier to understand answers. Rollout starts in ChatGPT, then API.MultimodalReleased 3mo ago
-
By OpenAIThe Thinking variant is the deeper-reasoning option. It adjusts how much thinking it does based on task difficulty, trading speed for accuracy when needed, and supports a user-visible thinking-time toggle in ChatGPT.MultimodalReleased 3mo ago
-
By OpenAIThe Instant variant is the fast, chat-first option in the 5.1 line. It favors low latency and solid instruction following, with long context, function calling, and reliable JSON. For most everyday prompts, the system router selects Instant by default.MultimodalReleased 3mo ago
-
By OpenAIGPT OSS Safeguard is a safety and policy companion model. It classifies risk, explains the rationale, suggests safe rephrasings, and returns structured JSON decisions for moderation and guardrails.TextReleased 3mo ago
-
By OpenAIGPT-Realtime is a low-latency multimodal model for live assistants. It understands text, images, and audio, and replies with text or natural speech. It supports function calling, long context, and clean JSON, so you can build voice-first apps that feel instant.MultimodalReleased 3mo ago
-
By OpenAIGPT-4.1 nano is the smallest, most efficient version of the series. Built for on-device and edge use, it provides lightweight reasoning and summarization with extremely low latency and cost, trading depth for portability.TextReleased 4mo ago
-
By OpenAIGPT-4.1 mini is the fast, efficient member of the family. It delivers strong reasoning and multimodal support with lower latency and cost than GPT-4.1, making it ideal for everyday assistants, customer support, and high-traffic apps.TextReleased 10mo ago
-
TextReleased 10mo ago
-
By OpenAIGPT-5 (Thinking) is OpenAI’s high-end reasoning variant of the GPT-5 series. It emphasizes deep, step-by-step analysis, long-context reasoning, and structured outputs—ideal for complex coding, math, research, and enterprise-grade agent workflows where accuracy is prioritized over latency.TextReleased 6mo ago
No models found
Try adjusting your search or filters.
