Models

GPT-5 is OpenAI’s new flagship reasoning model, powering the default ChatGPT experience and now exposed directly through the API. A larger transformer core is paired with a real-time router that orchestrates deep chain-of-thought, parallel tool calls, and multimodal reasoning, letting one request span tasks as varied as end-to-end app generation, legal analysis, or medical literature review. The API delivers the full “thinking” tier: every call can accept 272 000 input tokens and emit 128 000 reasoning-plus-output tokens, for a record 400 000-token context. Developers steer behaviour with two fresh dials—reasoning_effort (from minimal to high) and verbosity (low → high)—and can drop JSON in favour of custom tools defined by context-free grammars. Across OpenAI’s evals GPT-5 cuts hallucinations by ~80 %, scores 74.9 % on SWE-bench Verified, and reaches 97 % on τ²-bench tool use. Safety improvements include stricter self-evaluation and a new safe-completion strategy. Pricing is US $1.25 / M input tokens and US $10 / M output tokens, with prompt caching and batch endpoints to trim cost further.

GPT-5-Mini keeps the full developer surface—272 k / 128 k context, reasoning_effort, verbosity, custom tools, and multimodal support—while dialing down active experts to slash latency and memory. In internal measurements it replies roughly 40 % faster than the flagship yet still registers 91.1 % on the 2025 AIME math contest and 87.8 % on OpenAI’s aggregate “Intelligence” suite, comfortably outperforming o3 and rival compact models. The smaller footprint is ideal for high-traffic chat widgets, knowledge-base summarisation, edge analytics, and mobile agents where per-request cost dominates. Mini inherits GPT-5’s safer completion style and reduced hallucinations, making it suitable for customer-facing scenarios that once demanded the full model. Pricing lands at just US $0.25 / M input tokens and US $2 / M output tokens, so migrating from the flagship is as easy as swapping the model name and rerunning load tests. (OpenAI)

GPT-5-Nano pushes optimisation further for situations where every millisecond and cent count—voice assistants, real-time fraud filters, IoT gateways, or background content moderation. It retains the same enormous 400 k context window and tool-calling APIs but runs an aggressively quantised expert mix that triples tokens-per-second versus the flagship. Despite its size, Nano still scores 85.2 % on AIME 2025 and 75.6 % on MMMU multimodal reasoning, handily beating GPT-4.1-mini in code-generation and logic while using a fraction of the compute. Developers can combine Nano with the new minimal reasoning mode for sub-150 ms round-trips, yet fall back to higher effort on the same endpoint if deeper thought is occasionally required. At US $0.05 / M input tokens and US $0.40 / M output tokens, Nano unlocks billion-call workloads and on-device inference pilots without budget strain, all while benefiting from GPT-5’s upgraded safety guardrails and custom grammar-bound tool calls.

OpenAI GPT5 Chat is the dialog-tuned member of the GPT-5 family, built to anchor long, natural conversations in both ChatGPT and the Chat Completions API. It inherits the core GPT-5 architecture with its 400 k token window, multimodal reasoning, and JSON-based tool calling, yet layers on an extra “conversation controller” that tracks turn-level intent, speaker roles, and safety context so replies stay consistent across hundreds of messages. OpenAI’s router keeps latency low by starting each turn in the compact inference path and only activating the heavier “thinking” experts when the user signals deeper analysis. In internal evals this cut factual errors in chat by roughly 35 percent compared with GPT-4o, while still matching GPT-5 on SWE-bench Verified at the high reasoning setting.

ChatGPT-4o contains latest improvements for chat use cases, expected for testing/evaluation purpose. ChatGPT-4o also supports structured outputs, with up to 16k max output tokens GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

GPT 4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.

GPT 4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.

GPT-4.1 nano is the fastest, most cost-effective GPT 4.1 model.

OpenAI has introduced GPT-4.5, its latest and most advanced AI language model to date. This model enhances pattern recognition and the ability to draw connections, leading to more natural and intuitive interactions. GPT-4.5 is particularly adept at tasks such as writing assistance, programming, and practical problem-solving. Despite its advancements, OpenAI emphasizes that GPT-4.5 is not a frontier AI model and may not surpass specialized versions like o1 or o3-mini in certain areas. The model has been trained using a combination of new supervision techniques and traditional methods, resulting in fewer hallucinations and more emotionally nuanced responses. However, GPT-4.5 is more computationally intensive and expensive to operate compared to its predecessors. Initially, it is available as a research preview for ChatGPT Pro users, with plans to extend access to other user groups in the near future.

OpenAI has introduced GPT-4.5, its latest and most advanced AI language model to date. This model enhances pattern recognition and the ability to draw connections, leading to more natural and intuitive interactions. GPT-4.5 is particularly adept at tasks such as writing assistance, programming, and practical problem-solving. Despite its advancements, OpenAI emphasizes that GPT-4.5 is not a frontier AI model and may not surpass specialized versions like o1 or o3-mini in certain areas. The model has been trained using a combination of new supervision techniques and traditional methods, resulting in fewer hallucinations and more emotionally nuanced responses. However, GPT-4.5 is more computationally intensive and expensive to operate compared to its predecessors. Initially, it is available as a research preview for ChatGPT Pro users, with plans to extend access to other user groups in the near future.

This version’s creative writing ability has leveled up–more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses. GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

GPT 4o Mini ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

GPT-4o with structured outputs, with up to 16k max output tokens GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to Dec 2023. This model is updated by OpenAI to point to the latest version of [GPT-4 Turbo](/models?q=openai/gpt-4-turbo), currently gpt-4-turbo-2024-04-09 (as of April 2024).

Ability to understand images, in addition to all other [GPT-4 Turbo capabilties](/models/openai/gpt-4-turbo). Training data: up to Apr 2023. **Note:** heavily rate limited by OpenAI while in preview. #multimodal

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

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. Updated by OpenAI to point to the [latest version of GPT-3.5](/models?q=openai/gpt-3.5). Training data up to Sep 2021.

An experimental version of GPT-4o with a maximum of 64K output tokens per request. GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Sep 2021. This version has a higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.

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. Updated by OpenAI to point to the [latest version of GPT-3.5](/models?q=openai/gpt-3.5). Training data up to Sep 2021.

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. Updated by OpenAI to point to the [latest version of GPT-3.5](/models?q=openai/gpt-3.5). Training data up to Sep 2021.

The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Sep 2021.

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.

Similar capabilities as GPT-3 era models. Compatible with legacy Completions endpoint and not Chat Completions.

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to Dec 2023. This model is updated by OpenAI to point to the latest version of [GPT-4 Turbo](/models?q=openai/gpt-4-turbo), currently gpt-4-turbo-2024-04-09 (as of April 2024).

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to Dec 2023. This model is updated by OpenAI to point to the latest version of [GPT-4 Turbo](/models?q=openai/gpt-4-turbo), currently gpt-4-turbo-2024-04-09 (as of April 2024).

GPT-4 model with the ability to understand images, in addition to all other GPT-4 Turbo capabilities. This is a preview model, we recommend developers to now use gpt-4-turbo which includes vision capabilities.

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to Dec 2023. This model is updated by OpenAI to point to the latest version of [GPT-4 Turbo](/models?q=openai/gpt-4-turbo), currently gpt-4-turbo-2024-04-09 (as of April 2024).

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.

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.

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-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.

The latest GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Apr 2023. **Note:** heavily rate limited by OpenAI while in preview.

GPT-4-32k is an extended version of GPT-4, with the same capabilities but quadrupled context length, allowing for processing up to 40 pages of text in a single pass. This is particularly beneficial for handling longer content like interacting with PDFs without an external vector database. Training data: up to Sep 2021.

GPT-4-32k is an extended version of GPT-4, with the same capabilities but quadrupled context length, allowing for processing up to 40 pages of text in a single pass. This is particularly beneficial for handling longer content like interacting with PDFs without an external vector database. Training data: up to Sep 2021.