Quickstart

Get an API key from the dashboard and substitute it below. All examples use streaming, which is how most applications consume completions.

curl

curl -X POST https://api.pinstripes.io/v1/chat/completions \
  -H "Authorization: Bearer sk-ps-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ps/qwen3.6-35b-a3b",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-ps-...",
    base_url="https://api.pinstripes.io/v1",
)

stream = client.chat.completions.create(
    model="ps/qwen3.6-35b-a3b",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-ps-...",
  baseURL: "https://api.pinstripes.io/v1",
});

const stream = await client.chat.completions.create({
  model: "ps/qwen3.6-35b-a3b",
  messages: [{ role: "user", content: "Hello!" }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

The integration guides cover popular tools and frameworks including LM Studio, LangChain, and llm CLI.