One API for every model on GlobalGPT.

chat.py

from openai import OpenAI

client = OpenAI(
    api_key="sk-glb-...",
    base_url="https://api2.glbgpt.com/ai-api/open/v1",
)

r = client.chat.completions.create(
    model="gpt-6-astra",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True,
)
for chunk in r:
    print(chunk.choices[0].delta.content or "", end="")

Three steps

1Create a key

API → API Keys → Create key. Shown once, keep it safe.

2Pick a model

GET /v1/models lists every id with its price — gpt-6-astra, claude-opus-5, kling-v3…

3Call it

POST /v1/chat/completions for chat, POST /v1/tasks for image, video and audio.

Prefer a terminal? The same account works in the GlobalGPT CLI and MCP server.