OpenAI
OpenAI: GPT-4
openai/gpt-4
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.
Input
$30
/ 1M tokens
Output
$60
/ 1M tokens
Context window
8.19K
tokens
Limits
Context
8,191
tokens
Max output
4,096
50% of the context window
Model facts
Author
OpenAI
Tokenizer
GPT
Modality
Text -> Text
Knowledge cutoff
2021-09-30
Created
May 28, 2023
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · TextOutput · Text
Generation controls
Frequency penaltyLogit biasLogprobsMax completion tokensMax tokensPresence penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop logprobsTop p
Capability scores
13.1
Coding index
Better than 9% of models compared
6.7
Intelligence index
Better than 7% of models compared