AI Gateway quickstart

One endpoint, available models. Create a key, send a completion, watch the cost land on your usage page.

Prerequisites

A SetCloud account with billing set up — a saved card and the $50 starting credit deposit.

1. Create an API key

In the dashboard, open AI Gateway → API Keys and create a key. Keys start with sk-sc- and are shown once — copy it now.

export SETCLOUD_API_KEY="sk-sc-..."

2. List the models

curl https://setcloud.com/v1/models \
  -H "Authorization: Bearer $SETCLOUD_API_KEY"

Use an ID returned by this request. Availability changes; examples below use nova-micro or nova-lite, which must also appear in your own catalog. Embeddings use embed-text-v2; ready custom models have custom-* IDs.

3. Send a completion

curl https://setcloud.com/v1/chat/completions \
  -H "Authorization: Bearer $SETCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nova-micro",
    "messages": [{ "role": "user", "content": "Say hello in five words." }]
  }'

The response is OpenAI-shaped: choices[0].message.content holds the reply, usage holds the token counts you were billed for.

4. Point your existing SDK at it

The API is OpenAI-compatible. Swap the base URL and the key and choose a model returned by your catalog. Only the documented endpoints and model capabilities are supported.

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.SETCLOUD_API_KEY,
  baseURL: 'https://setcloud.com/v1',
});

const res = await client.chat.completions.create({
  model: 'nova-lite',
  messages: [{ role: 'user', content: 'Summarize this repo in one line.' }],
});
console.log(res.choices[0].message.content);

5. Watch your usage

AI Gateway → Usage shows tokens and cost per request. Usage draws down your prepaid credits — rates are on the pricing page.

API reference — full request/response schemas, tool calling, streaming, errors, rate limits.
Embeddings — turn text into vectors with POST /v1/embeddings.
Try models interactively in AI Gateway → Playground.
Fine-tune a model on your own data from AI Gateway → Fine-tuning.