OpenAI: GPT-4
- by openai
- 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...
What the numbers mean
- Context window8,191 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 6,100 words, or 12 pages.
- Max output4,096 tokens
- The longest single reply it can write: about 3,100 words.
- Input price$30 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs about $0.04.
- Output price$60 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs about $0.04.
- Modalitiestext in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
- Knowledge cutoff2021-09-30
- The last date its training data covers. It does not know about anything after that unless you put it in the prompt.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
frequency_penaltylogit_biaslogprobsmax_completion_tokenspresence_penalty