1. Get an API key
Sign up, open the dashboard, and create a key from the API Keys page. Keys start with sk-live-. Your first $5 trial covers a full day of testing every model.
2. Python (OpenAI SDK)
pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.plugsky.com/v1",
api_key="sk-live-...", # your key
)
resp = client.chat.completions.create(
model="plugsky-pro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
3. Node.js (OpenAI SDK)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.plugsky.com/v1",
apiKey: "sk-live-...",
});
const resp = await client.chat.completions.create({
model: "plugsky-lite",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);
4. cURL
curl https://api.plugsky.com/v1/chat/completions \
-H "Authorization: Bearer sk-live-..." \
-H "Content-Type: application/json" \
-d '{"model":"plugsky-pro","messages":[{"role":"user","content":"Hello!"}]}'
5. Streaming
resp = client.chat.completions.create(
model="plugsky-pro",
messages=[{"role": "user", "content": "Count to 5"}],
stream=True,
)
for chunk in resp:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")
6. Pick a model
- Speed first — plugsky-lite (~0.24s) or plugsky-phi.
- Balanced — plugsky-plus (~0.80s).
- Reasoning — plugsky-pro (~0.67s) or plugsky-max.
- Frontier — plugsky-frontier (Mistral Large 3 675B).
- Embeddings — plugsky-embed (2,048 dims) or plugsky-embed-multilingual (4,096 dims).
Quickstart FAQ
Do I have to rewrite my code?
No. If you use the OpenAI SDK, only the base_url (and model names) change. See the switch guide.
What are the rate limits?
Limits depend on your plan and are visible in the dashboard.
Where can I test without code?
The playground and playground beta work without a key.
Get started in minutes
OpenAI-compatible API with 30+ models, free trial, and a 99.9% uptime SLA. No code changes required.
Start free trial → Read the docs