#GPT-4

1 messages · Page 1 of 1 (latest)

wary ridge
#

Documentation

rocky falconBOT
#

Hi @wary ridge. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

GPT-4 is a large multimodal model developed by OpenAI. It accepts text or image inputs and outputs text. It can solve difficult problems with greater accuracy than any of OpenAI's previous models, thanks to its broader general knowledge and advanced reasoning capabilities. GPT-4 is available in the OpenAI API to paying customers and is optimized for chat but also works well for traditional completions tasks using the Chat Completions API [source] (https://platform.openai.com/docs/models).

There are several versions of GPT-4, including gpt-4-0613, gpt-4-32k-0613, gpt-4-0314Legacy, and gpt-4-32k-0314Legacy. These versions have different token limits and were released at different times. Some of these versions will be deprecated in the future [source] (https://platform.openai.com/docs/models).

GPT-4 powers numerous innovative products, including GitHub Copilot, Replit, and Cursor. It is more advanced than previous models like text-davinci-002 [source] (https://cookbook.openai.com/articles/how_to_work_with_large_language_models#code-capabilities).

GPT-4 also outperforms both previous large language models and most state-of-the-art systems as of 2023. It demonstrates strong performance not only in English but also in other languages [source] (https://platform.openai.com/docs/models).

Access to GPT-4 is available to Pay-As-You-Go customers who have made a successful payment of $1 or more. ChatGPT Plus subscribers also get GPT-4 access with a usage cap [source] (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4).

#

GPT-4 Turbo is the latest generation model. It’s more capable, has an updated knowledge cutoff of April 2023, and introduces a 128k context window. The model is also 3X cheaper for input tokens and 2X cheaper for output tokens compared to the original GPT-4 model. The maximum number of output tokens for this model is 4096 [source] (https://help.openai.com/en/articles/8555510-gpt-4-turbo).

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@wary ridge kapa.ai is still learning and improving, please let us know how it did by reacting below

wary ridge
#

Is this chat private?

gray gate
#

nope