Integrations
Connect an OpenAI-compatible client to your workspace.
Connection settings
OPENAI_BASE_URL=https://api.unrefused.com/v1
OPENAI_API_KEY=YOUR_API_KEYUse these values in a client that supports a custom OpenAI-compatible endpoint. The exact configuration keys vary by client and version.
Choose a model
Discover available IDs with GET /v1/models. Use the model ID exactly as returned; display names are not interchangeable with API identifiers.
API compatibility
The supported interface is chat completions, including streaming and tool-call messages where the connected model supports them. Clients that require an Anthropic Messages or Responses endpoint need an adapter.
Try a request
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.unrefused.com/v1",
)
response = client.chat.completions.create(
model="glm-5.3-uncensored",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Availability depends on your connected provider. Check service status and keep x-request-id with your diagnostics.