Models
GPT
GPT-4 is OpenAI’s most advanced system, producing safer and more useful responses.
Tabs
With broad general knowledge and domain expertise, GPT-4 can follow complex instructions in natural language and solve difficult problems with accuracy.
GPT-4 is more creative and collaborative than ever before. It can generate, edit, and iterate with users on creative and technical writing tasks, such as composing songs, writing screenplays, or learning a user’s writing style.
GPT-4 can accept images as inputs and generate captions, classifications, and analyses.
GPT-4 is capable of handling over 25,000 words of text, allowing for use cases like long form content creation, extended conversations, and document search and analysis.
DALL·E
DALL·E is an AI system that can create realistic images and art from a description in natural language.
Tabs
DALL·E 2 can create original, realistic images and art from a text description. It can combine concepts, attributes, and styles.
Output
Output Navigation
DALL·E 2 can expand images beyond what’s in the original canvas, creating expansive new compositions.
DALL·E 2 can make realistic edits to existing images from a natural language caption. It can add and remove elements while taking shadows, reflections, and textures into account.
Output
Output Navigation
DALL·E 2 can take an image and create different variations of it inspired by the original.
Output
Output Navigation
Whisper
Whisper is a versatile speech recognition model that can transcribe, identify, and translate multiple languages.
Whisper can transcribe speech into text and translate many languages into English.
Made for developers
completion = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What are some famous astronomical observatories?"}
]
)Chat
Developers can use GPT-3 to build interactive chatbots and virtual assistants that can carry out conversations in a natural and engaging manner.Embeddings
With GPT-3, developers can generate embeddings that can be used for tasks like text classification, search, and clustering.Analysis
Developers can use GPT-3 to summarize, synthesize, and answer questions about large amounts of text.Fine-tuning
Developers can fine-tune GPT-3 on a specific task or domain, by training it on custom data, to improve its performance.
Ensuring responsible use of our models
null links
