Authentication

All requests to api.mantler.ai must include an API key in the Authorization header.

Authorization: Bearer mk_live_YOUR_KEY

---

Key format

Live API keys use the prefix mk_live_. Keys are generated from the API keys page in the Mantler web app.

---

Org scoping

Each API key is bound to an organization. It can only access mantles and machines that belong to that org. Keys are not transferable across orgs.

---

Key restrictions

When creating a key, you can optionally restrict it to:

• Specific mantles (by mantle ID)
• Specific machines
• A rate limit (requests per minute / tokens per minute)

A key with no restrictions has access to all deployed mantles in the org.

---

Revoking a key

Keys can be revoked at any time from the web app. Revoked keys are rejected immediately at the gateway — there is no grace period.

---

Using your key

curl:

curl https://api.mantler.ai/v1/chat/completions \
  -H "Authorization: Bearer mk_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Python (openai SDK):

from openai import OpenAI

client = OpenAI(
    api_key="mk_live_YOUR_KEY",
    base_url="https://api.mantler.ai/v1",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Node.js (openai SDK):

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'mk_live_YOUR_KEY',
  baseURL: 'https://api.mantler.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'YOUR_MODEL_ID',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(response.choices[0].message.content);