OpenAI
OpenAI

GPT-4 Vision

openai/gpt-4-vision-preview

Ability to understand images, in addition to all other GPT-4 Turbo capabilties. Training data: up to Apr 2023.

Note: heavily rate limited by OpenAI while in preview.

#multimodal

Capability

Vision Support

Context Window

128,000

Max Output Tokens

4,096

Language

PythonJavaScriptCurl

Using GPT-4 Vision with Python API

Using GPT-4 Vision with OpenAI compatible API

import openai

client = openai.Client(
  api_key= '{your_api_key}',
  base_url="https://api.model.box/v1",
)
response = client.chat.completions.create(
model="openai/gpt-4-vision-preview",
messages: [
  {
    role: 'user',
    content:
      'introduce your self',
    },
  ]
)
print(response)