Quickstart

Send your first request in three steps: discover the models your key can call, pick one, then issue a chat-completion call against the base URL.

1. List your models

Use GET /v1/models with your key to see only the models your tier includes.

curl
curl https://api.boltch.cloud/v1/models \
  -H "Authorization: Bearer YOUR_BOLTCH_KEY"

2. Issue a streaming chat completion

curl
curl https://api.boltch.cloud/v1/chat/completions \
  -H "Authorization: Bearer YOUR_BOLTCH_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-sol",
    "stream": true,
    "messages": [{"role":"user","content":"Hello from Boltch."}]
  }'

3. Or use the OpenAI Node SDK

Boltch is OpenAI-compatible. Swap baseURL and reuse your existing SDK.

Node.js
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.BOLTCH_API_KEY,
  baseURL: "https://api.boltch.cloud/v1",
});

const stream = await client.chat.completions.create({
  model: "gpt-6-sol",
  stream: true,
  messages: [{ role: "user", content: "Build me a plan." }],
});

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

4. Check usage

Open the dashboard to view monthly requests, token totals, cache hits, and per-model spend.