Developers

Built for developers

Every server is reachable over SSH and through our API. Automate launches, call models from your code and keep secrets out of the container.

Full API reference

SSH into any server

Add your public key in the dashboard. The user name is the server id; any Docker image works, no sshd needed.

bash

ssh -p 2222 [email protected]

# copy files
scp -P 2222 data.zip [email protected]:/workspace/

Open web UIs through a tunnel

Forward ComfyUI, Jupyter or Open WebUI to your computer and open http://localhost in the browser.

bash

# ComfyUI on http://localhost:8188
ssh -p 2222 -N -L 8188:localhost:8188 [email protected]

# Jupyter Lab on http://localhost:8888 (token in the dashboard)
ssh -p 2222 -N -L 8888:localhost:8888 [email protected]

Launch servers with the API

Create an API key in the dashboard and pass it as a Bearer token.

bash

curl https://api.gysga.com/v1/instances \
  -H "Authorization: Bearer $GYSGA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"gpu_model": "rtx-4090", "gpu_count": 1,
       "template": "vllm", "model": "qwen3-8b"}'

# list, stop, start, destroy
curl -H "Authorization: Bearer $GYSGA_API_KEY" https://api.gysga.com/v1/instances
curl -X POST   -H "Authorization: Bearer $GYSGA_API_KEY" https://api.gysga.com/v1/instances/i-a1b2c3d4/stop
curl -X DELETE -H "Authorization: Bearer $GYSGA_API_KEY" https://api.gysga.com/v1/instances/i-a1b2c3d4

Call your model like OpenAI

vLLM, SGLang, Ollama and speaches templates speak the OpenAI API. Point any OpenAI SDK at your server through our proxy: your Gysga key is checked and stripped before the request reaches the container.

curl

curl https://api.gysga.com/v1/instances/i-a1b2c3d4/proxy/8000/v1/chat/completions \
  -H "Authorization: Bearer $GYSGA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "Qwen/Qwen3-8B",
       "messages": [{"role": "user", "content": "Hello!"}]}'

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gysga.com/v1/instances/i-a1b2c3d4/proxy/8000/v1",
    api_key="gsk_...",  # your Gysga API key
)
reply = client.chat.completions.create(
    model="Qwen/Qwen3-8B",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)
for chunk in reply:
    print(chunk.choices[0].delta.content or "", end="")