GPT Models

GPT Models

The OpenAI API is supported by a varied range of GPT Models. Each model offering distinct functionalities and available at various pricing levels. Additionally, these models can be tailored through fine-tuning to meet the specific needs of your application.

ModelDescription
GPT-6Gathering training data
GPT-5Under training for today (Q1 2024)
GPT-4 & GPT-4 TurboModels enhancing GPT-3.5 capabilities, adept in interpreting and producing both text and code.
GPT-3.5 TurboModels advancing upon GPT-3.5, skilled in comprehending and crafting text and code.
GPT baseModels focusing on understanding and generating text and code, sans instruction following.
GPT Models list

GPT-6

Gathering training data

GPT-5

Under training for today (Q1 2024)

GPT-4 & GPT-4 Turbo

GPT-4, along with GPT-4 Turbo, represents the latest advancement in OpenAI’s suite of multimodal models. They capable of interpreting both textual and visual inputs to generate textual outputs. These models mark a significant leap over their predecessors by solving complex problems with unmatched accuracy, thanks to their extensive knowledge base and superior reasoning skills. Available to subscribers via the OpenAI API. GPT-4 is particularly designed for chat applications, though it is equally adept at handling traditional completion tasks. Detailed instructions for employing GPT-4 in text generation projects are provided for users’ benefit.

Here’s a breakdown of the various GPT-4 models:

ModelDescriptionContext WindowTraining Data
gpt-4-0125-previewThe latest iteration of GPT-4 Turbo designed to minimize “laziness,” capable of producing up to 4,096 tokens.128,000 tokensUp to Dec 2023
gpt-4-turbo-previewDirects to gpt-4-0125-preview.128,000 tokensUp to Dec 2023
gpt-4-1106-previewGPT-4 Turbo variant with enhanced features like JSON mode, consistent outputs, and parallel processing, offering up to 4,096 tokens.128,000 tokensUp to Apr 2023
gpt-4-vision-previewGPT-4 model capable of processing images alongside possessing all Turbo features, linking to gpt-4-1106-vision-preview.128,000 tokensUp to Apr 2023
gpt-4-1106-vision-previewGPT-4 variant with image understanding and full Turbo functionalities, also generating up to 4,096 tokens.128,000 tokensUp to Apr 2023
gpt-4Refers to gpt-4-0613, indicating continuous model enhancements.8,192 tokensUp to Sep 2021
gpt-4-0613A snapshot of GPT-4 from June 13th, 2023, with improved function calling feature.8,192 tokensUp to Sep 2021
gpt-4-32kPoints to gpt-4-32k-0613, a model superseded by GPT-4 Turbo despite its upgrades.32,768 tokensUp to Sep 2021
gpt-4-32k-0613A version of gpt-4-32k from June 13th, 2023, enhanced for better function calling, not widely released.32,768 tokensUp to Sep 2021
GPT-4 variations

GPT-4 Multilingual capabilities

GPT-4 surpasses earlier large language models and, as of 2023, most cutting-edge systems that typically rely on training tailored to specific benchmarks or extensive manual configuration. Utilizing the MMLU benchmark—a collection of multiple-choice questions in English spanning 57 topics—GPT-4 not only significantly exceeds the capabilities of previous models in English but also showcases robust proficiency across various other languages. This achievement highlights GPT-4’s versatility and its advanced understanding and processing of multilingual content.

GPT-3.5 Turbo

GPT-3.5 Turbo models are designed to comprehend and produce both natural language and code, having been fine-tuned for chat interactions through the Chat Completions API. Despite this specialization, they are also highly effective in handling tasks beyond chat-based applications.

Here’s the information presented in a structured table format along with a slight rephrasing:

ModelDescriptionContext WindowTraining Data
gpt-3.5-turbo-0125An upgraded version of GPT-3.5 Turbo that enhances accuracy in generating responses in specified formats and addresses a bug affecting text encoding for non-English function calls. Capable of producing up to 4,096 tokens.16,385 tokensUp to Sep 2021
gpt-3.5-turboCurrently linked to gpt-3.5-turbo-0613. It will automatically update from gpt-3.5-turbo-0613 to gpt-3.5-turbo-0125 on February 16th.4,096 tokensUp to Sep 2021
gpt-3.5-turbo-1106This model version of GPT-3.5 Turbo has been refined for better adherence to instructions, JSON mode, consistent outputs, and simultaneous function execution. It also supports up to 4,096 output tokens.16,385 tokensUp to Sep 2021
gpt-3.5-turbo-instructFeatures capabilities akin to GPT-3 era models. It is designed for the legacy Completions endpoint rather than the Chat Completions.4,096 tokensUp to Sep 2021
gpt-3.5-turbo-16kLegacy model currently referring to gpt-3.5-turbo-16k-0613.16,385 tokensUp to Sep 2021
gpt-3.5-turbo-0613Legacy snapshot as of June 13th, 2023, set to be deprecated on June 13, 2024.4,096 tokensUp to Sep 2021
gpt-3.5-turbo-16k-0613Legacy snapshot of gpt-3.5-16k-turbo from June 13th, 2023, also due for deprecation on June 13, 2024.16,385 tokensUp to Sep 2021
This table provides a concise overview of the various GPT-3.5 Turbo models, highlighting their unique features, capabilities, and the context window sizes they operate within, all based on training data available up to September 2021.

Read more about GPTs in our Blog.