| title | Try Auxen |
|---|---|
| emoji | 🤖 |
| colorFrom | blue |
| colorTo | indigo |
| sdk | gradio |
| sdk_version | 4.44.0 |
| app_file | app.py |
| pinned | true |
| license | apache-2.0 |
| short_description | Chat with a private AI model on Auxen |
Interactive chat demo for Auxen — private AI model endpoints on dedicated GPUs, OpenAI-compatible, pay-per-minute.
This Space lets you try Auxen in your browser without signing up. The demo uses a shared Auxen instance and rate-limits requests per session. For real use, provision your own private instance at auxen.ai — every call goes to your own GPU, no shared inference.
pip install auxenfrom auxen import Auxen
client = Auxen(
base_url="https://api.auxen.ai/v1/inst_xxx", # from your dashboard
api_key="auxk_...",
)
response = client.chat.completions.create(
model="llama-3.1-8b",
messages=[{"role": "user", "content": "Hello"}],
)Pricing: $0.10/hr (Small models) → $1.50/hr (XL 70B). No subscriptions, no per-token fees.