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.

ChatOpenAI8k tokens$32.7018 / $65.4036 · 1M

openai/gpt-4

Context
8k tokens
Completion cap
4,096
Tools
Yes
JSON
Yes
Released
2023-05-28

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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. GPT-4 runs on the Geek Hub API (OpenAI-compatible). Model id: openai/gpt-4.
Is GPT-4 free?
No. Input is $32.7018 per 1M tokens and output is $65.4036 per 1M tokens on Geek Hub (markup included).
What is the context length of GPT-4?
GPT-4 has a 8k tokens context window. It supports up to 4,096 completion tokens.
Does GPT-4 support tool calling and structured outputs?
GPT-4 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was GPT-4 released?
GPT-4 was released on 2023-05-28.

More models from OpenAI