Try For Free
Sign Up
85
Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.
Revolutionary AI model for unparalleled natural language interaction. API for ChatGPT 4.
High-speed AI model for instant language processing. API for ChatGPT 4 Turbo.
GPT Audio is OpenAI's latest flagship model capable of understanding and generating text and audio in real-time, designed for natural conversation and auditory tasks.
GPT Mini Audio adds speech-to-text and text-to-speech abilities to the efficient GPT Mini model, optimized for voice interfaces in smaller applications.
The newest GPT-3.5 Turbo with improved accuracy and encoding.
OpenAI's GPT-3.5-Turbo-Instruct: Streamlined AI for precise, instruction-driven interactions.
GPT-4o integrates text, vision, and audio for multimodal AI applications.
Multimodal AI model by OpenAI enhancing human-computer interaction.
GPT-4o Mini: Cost-efficient, advanced model for diverse AI applications.
GPT Audio is purpose-built for high fidelity conversational experiences, automating speech analytics and enabling new forms of voice-driven intelligence.
GPT Audio Mini is a lightweight speech synthesis model tailored for voice generation with minimal latency and computational demands.
GPT Chat Latest on AIMLAPI.
GPT Image 1 Mini transforms text prompts and optional image inputs into high-quality images, allowing precise control over generation parameters such as resolution, quality settings, and artistic style.
GPT Image 1 is OpenAI's first-generation image generation model combining language understanding with visual synthesis.
GPT Image 1.5 is OpenAI’s latest image model that generates sharp, highly prompt-faithful visuals and handles edits/variations reliably for production workflows.
GPT Image 2 (gpt-image-2) is OpenAI's most capable image generation model to date — reason before it draws, search the web in real time, and render production-ready text in over a dozen languages.
GPT Image 2.5 Flare is the speed-oriented tier of OpenAI's GPT Image 2.5 family, built for high-quality everyday image generation and editing.
GPT Image 2.5 Sunburst generates and edits images from text and image inputs, and is the tier OpenAI recommends where editing precision matters most.
Rolling alias that always points to OpenAI's current latest Mini-tier model — a lightweight option for cost-sensitive workloads without pinning to a specific version.
GPT OSS 120B is a large-scale open-source language model with 120 billion parameters, designed for advanced reasoning, code generation, and extended context processing.
OpenAI’s GPT OSS 20B offers flexible reasoning levels, agentic features, and robust coding support in an open-source, memory-efficient transformer.
OpenAI's chat-tuned model for conversation and general text generation, with a 16K-token context window and function calling support.
GPT-4.1 is OpenAI's large-context language model with up to 1M token input and improved instruction following.
GPT-4.1 mini is a cost-effective variant of GPT-4.1 with 1M token context, optimized for speed and efficiency.
GPT-4.1 nano is the most lightweight GPT-4.1 variant, designed for minimal latency and resource usage.
GPT-4o Mini Transcribe excels in delivering fast, cost-efficient, and highly accurate audio transcriptions, especially in noisy and accented speech conditions.
GPT-4o mini TTS is a text-to-speech model built on GPT-4o mini, a fast and powerful language model. Use it to convert text to natural sounding spoken text with customizable voice characteristics through instructions. The maximum number of input tokens is 2000.
GPT-4o Transcribe is a highly advanced speech-to-text model combining deep learning and extensive audio training to deliver reliable transcriptions with strong contextual understanding.
GPT-5 is OpenAI's latest advanced large language model featuring a 400K token context window and unified multimodal capabilities including text, images, and audio.
GPT-5 Image on AIMLAPI.
GPT-5 Image Mini on AIMLAPI.
GPT-5 Mini offers a lightweight yet powerful solution within the GPT-5 lineup, delivering efficient multimodal AI with text and vision inputs.
GPT-5 nano is a lightweight, high-efficiency variant of the GPT-5 large language model, offering ultra-fast, cost-effective multimodal AI capabilities.
GPT-5 Pro stands at the pinnacle of current large language model technology, providing unparalleled accuracy and reasoning power for enterprise applications.
GPT-5.1 is an optimized iteration that focuses on refining usability, enhancing communication capabilities, and delivering higher-quality results.
GPT-5.1 Codex builds on the GPT-5.1 architecture, tailored for interactive coding assistance and large-scale engineering projects.
GPT-5.1 Codex Mini is the ideal choice for developers and teams seeking a lightweight, fast, and reliable AI assistant for coding tasks.
GPT-5.1-Codex-Max on AIMLAPI.
GPT-5.2 is OpenAI’s most advanced model series to date, engineered specifically for high-stakes knowledge work.
For organizations and developers seeking to build reliable, scalable, and intelligent development workflows, GPT-5.2 Codex API offers a powerful and future-ready foundation.
GPT‑5.2 Pro sets new state-of-the-art records across professional, academic, and reasoning domains.
The most capable agentic coding model ever built, combining frontier coding, deep reasoning, and full computer-use into one model that works with you, not just for you.
A high-performance large language model engineered for advanced reasoning, multimodal understanding, long-context processing, and real-world coding tasks.
GPT-5.4 Image 2 on AIMLAPI.
GPT-5.4 Mini on AIMLAPI.
GPT-5.4 Nano on AIMLAPI.
OpenAI's most capable and intuitive frontier model to date, built for agentic coding, real computer use, and knowledge work that actually gets done without hand-holding.
OpenAI's newest flagship is a fully retrained base model built from the ground up for real work: agentic coding, complex knowledge tasks, computer use, and scientific research.
GPT-5.6 is OpenAI's model family released July 9, 2026, spanning three tiers — Sol, Terra, and Luna — with stronger coding, science, and cybersecurity capabilities.
OpenAI's extended-reasoning configuration of GPT-5.6 Luna, trading speed for deeper reasoning on complex requests, with a 1M-token context window.
Extended-reasoning variant of GPT-5.6 Sol — OpenAI's flagship model for frontier coding and multi-step reasoning — built for tasks where correctness matters more than response speed, with a 1M-token context window and image input.
Extended-reasoning variant of GPT-5.6 Terra — OpenAI's mid-tier model between Sol and Luna — built for tasks where accuracy matters more than response speed, with a 1M-token context window and support for image input.
GPT-6 Astra is OpenAI's most capable model, built for long end-to-end work across complex reasoning, coding, computer use and research.
GPT-6 Luna is OpenAI's most efficient model for focused, high-volume tasks — the cheapest tier of the GPT-6 family, with the same 1,050,000-token context window as the larger models.
GPT-6 Sol is OpenAI's model for complex coding and agentic workflows, sitting below the flagship GPT-6 Astra with the same 1,050,000-token context window at a fifth of the price.
GPT-6.1 model from OpenAI with near-Astra performance at a lower cost for complex coding, computer use and professional work: text and image input over a 1.05M-token context, with reasoning, and tool calling and server tools via the Responses API.
OpenAI o4-mini is a compact reasoning model that delivers strong performance with lower latency and cost.
gpt-oss-safeguard-20b on AIMLAPI.
A reasoning-optimized large language model built for high-stakes analytical work, long-form document processing, and multi-step problem solving, where accuracy actually matters.
OpenAI o1 excels in complex reasoning tasks with advanced features like chain-of-thought processing and extensive context support.
New AI model from OpenAI for complex reasoning in science, coding, and mathematics.
o1-pro on AIMLAPI.
OpenAI o3-mini excels in reasoning tasks with advanced features like deliberative alignment and extensive context support.
Build AI assistants with custom instructions and tool usage
OpenAI o3 is a frontier reasoning model with exceptional performance on complex scientific, math, and coding tasks.
o3‑Pro is OpenAI’s advanced model focused on precision, reasoning, and reliability for enterprise and developer use.
Sora 2 is OpenAI’s next-generation video model, built to transform text and images into cinematic, high-fidelity video.
Featuring synchronized spatial audio and advanced physics simulations, it enables realistic motion and soundscapes, elevating AI-generated videos to professional cinematic standards.
Sora 2 Pro is OpenAI’s advanced, professional-grade AI platform that turns written ideas and visual cues into cinematic video content.
Designed for creators and developers demanding cinematic quality, this model excels at preserving visual consistency, realistic physics, and synchronized sound.
Sora 2 Pro generates high-fidelity, longer-duration videos from text prompts with enhanced cinematic quality.
High-performance embedding model with flexible dimensions and superior accuracy.
OpenAI's efficient text embedding model for semantic search and similarity tasks at lower cost.
Reliable embedding model offering solid performance for various tasks.
TTS-1 is a real-time text-to-speech model optimized for speed. Provides lower latency but at a lower quality than TTS-1 HD.
TTS-1 HD is a high-quality text-to-speech model that provides superior audio quality compared to TTS-1.
Whisper: Multilingual speech recognition model, robust, versatile, open-source.
