Quickstart

Get an API key, send your first request, and stream a response.

1. Create an API key

Head to the developer platform → API Keys → Create new key. Copy it now — you won't be able to see it again.

2. Set your key

export CINDER_API_KEY="sk-cinder-..."

3. Your first request

Cinder is OpenAI-compatible, so you can use curl or any OpenAI SDK.

cURL

curl https://cinder-pn3.pages.dev/v1/chat/completions \
  -H "Authorization: Bearer $CINDER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{ "role": "user", "content": "Explain black holes in one line." }]
  }'

JavaScript / TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://cinder-pn3.pages.dev/v1",
  apiKey: process.env.CINDER_API_KEY,
});

const res = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Explain black holes in one line." }],
});

console.log(res.choices[0].message.content);

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://cinder-pn3.pages.dev/v1",
    api_key=os.environ["CINDER_API_KEY"],
)

res = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Explain black holes in one line."}],
)
print(res.choices[0].message.content)

4. Stream the response

Set stream: true to receive tokens as server-sent events:

const stream = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Write a haiku about embers." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Next steps