API documentation

MuggleLink exposes an OpenAI-compatible REST API. If your code already talks to OpenAI, you can switch by changing two values: the base URL and the API key.

Base URL

https://api.mugglelink.com/api/v1

Authentication

Authenticate every request with a bearer token — the API key you create on /dashboard/keys. Keys look like mk_live_….

Authorization: Bearer <your-api-key>

Keep your API key secret. Anyone with the key can spend your account balance. Never share it in client-side code, a public repository, or a support ticket.

Quickstart examples

curl

curl https://api.mugglelink.com/api/v1/chat/completions \
  -H "Authorization: Bearer $MUGGLELINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.mugglelink.com/api/v1",
    api_key="mk_live_...",   # your MuggleLink API key
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Node.js (openai SDK)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.mugglelink.com/api/v1",
  apiKey: "mk_live_...", // your MuggleLink API key
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Streaming

Set stream: true to receive a Server-Sent Events (SSE) stream of incremental deltas, identical in shape to OpenAI's streaming format.

curl https://api.mugglelink.com/api/v1/chat/completions \
  -H "Authorization: Bearer $MUGGLELINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "stream": true,
    "messages": [{ "role": "user", "content": "Count to 5." }]
  }'

Usage and cost are calculated once the stream completes, from the final chunk, and billed the same as a non-streaming request.

Endpoint reference

POST/api/v1/chat/completions

Create a model response for the given chat conversation. Accepts the same body as OpenAI's Chat Completions API: model, messages, stream, temperature, and other standard sampling parameters are passed through to the upstream model unchanged.

GET/api/v1/models

List every model available for use, in OpenAI's list format. This is the same source of truth used to bill your requests and to render /models.

Error codes

Status	Type	Meaning
400	invalid_request_error	The request body is malformed or references a model that doesn't exist.
401	invalid_api_key	The Authorization header is missing or the API key is invalid or revoked.
402	insufficient_credits	Your account balance is $0.00 or lower. Top up to continue making requests.
429	rate_limit_exceeded	Too many requests in a short period. Slow down and retry.
500	upstream_error	The upstream model provider returned an error. You were not charged.

A 402 response looks like this:

{
  "error": {
    "message": "Insufficient credits. Top up at https://mugglelink.com/topup",
    "type": "insufficient_credits",
    "code": 402
  }
}