OpenAI: gpt-4 API
GPT-4 is a large multimodal model by OpenAI, accepting image and text inputs. It demonstrates human-level performance on professional and academic benchmarks. Built on a Sparse MoE architecture with 16 experts, it provides profound logic and knowledge depth.
- Context window: 8,192 tokens
- Max output: 8,192 tokens
- Input: text
- Output: text
- Tool calling: Supported
- File input: Supported
- Released: 2023-11-06
- Knowledge cutoff: 2023-11-30
Frequently Asked Questions
What is the context window of gpt-4?
gpt-4 supports a context window of up to 8,192 tokens.
Does gpt-4 support function calling?
Yes. gpt-4 supports tool / function calling.
What is the knowledge cutoff of gpt-4?
The knowledge cutoff of gpt-4 is 2023-11-30.