Chat Completions

Request

Chat Competions (POST)

Headers

Name	Value
Authorization	Bearer <token>

Body

Name	Type	Description
messages*	list	Messages
model*	string	Model
stream	boolean	Stream
temperature	float	Temperature
max_tokens	integer	Max tokens

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_TOKEN", base_url="https://api.gpt4-all.xyz/v1")

response = client.chat.completions.create(
    model="gpt-4.1-mini",
    messages=[{"role": "user", "content": "hi"}],
    stream=False,
)

print(response.choices[0].message.content)

Python Stream

from openai import OpenAI

client = OpenAI(api_key="YOUR_TOKEN", base_url="https://api.gpt4-all.xyz/v1")

response = client.chat.completions.create(
    model="gpt-4.1-mini",
    messages=[{"role": "user", "content": "hi"}],
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="")

Python Vision

from openai import OpenAI

client = OpenAI(api_key="YOUR_TOKEN", base_url="https://api.gpt4-all.xyz/v1")
start = time.time()

response = client.chat.completions.create(
  model="gpt-4.1-mini",
  messages=[
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "whats on the image?"},
        {
          "type": "image_url",
          "image_url": {
            "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
          },
        },
      ],
    }
  ],
  max_tokens=300,
)

print(response.choices[0].message.content)