Build on the Sonichaos API

Install

There is no Sonichaos SDK to install. The gateway speaks the OpenAI wire format, so your existing OpenAI client works unchanged — you only change the base URL and the key.

npm install openai
# or
pip install openai

Quickstart

1. Get an API key

An organisation admin mints keys with POST /api/apikeys. The raw key is returned once; the server keeps only a hash.

curl https://sonichaos.ai/api/apikeys \
  -H "Authorization: Bearer $SONICHAOS_SESSION" \
  -H "Content-Type: application/json" \
  -d '{"name":"quickstart"}'

# → { "id": "key_…", "name": "quickstart", "prefix": "sk_live_…", "key": "sk_live_…" }

2. Set the base URL

Point your client at https://sonichaos.ai/v1 for chat, and https://sonichaos.ai/api for the control API.

3. Make your first chat call

Any model id returned by GET /v1/models works. Streaming is supported with stream: true.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SONICHAOS_API_KEY,
  baseURL: "https://sonichaos.ai/v1",
});

const chat = await client.chat.completions.create({
  model: "gpt-4o", // any id from GET /v1/models
  messages: [{ role: "user", content: "Say hello in one word." }],
  max_tokens: 16,
});

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

Or with curl:

curl https://sonichaos.ai/v1/chat/completions \
  -H "Authorization: Bearer $SONICHAOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Say hello in one word."}],"max_tokens":16}'

API reference

Two surfaces, one credential model. Both authenticate with Authorization: Bearer <token> — the gateway takes an API key or a sandbox token, and the platform API takes a session token.

OpenAI-compatible gateway · /v1

Platform API · /api